ai.forkmate/forkmate
ForkMate
Effortless calorie tracking for people who train — just tell your AI what you ate.
DECISION SUMMARY
Allow With Approval
Score
73.8
Top 8.7% of 287 scored public servers
Confidence
High
Based on evidence completeness, recency, and validation density.
Evidence age
20.1h old
Freshness: fresh. Snapshot
trustsnap_bdffe6a1dc7e6fcc.Top risk drivers
- Transport Compliance
- Recovery Semantics
- Error Contract
Recommended actions
- Add an explicit confirm/dry-run parameter or two-step confirmation flow to write, delete, exec, and egress-capable tool…
- Align MCP-Protocol-Version, MCP-Session-Id, DELETE teardown, and expired-session handling with the transport spec.
- Only send roots/list, sampling/createMessage, or elicitation/create requests while handling an active client-initiated…
Next action
export policy, require approval for writes, add authenticated validation
exec-capable tools + no confirmation safeguards + high-risk tools need review + unauthenticated behavior not proven
Observed Attention
No observed attention
No observed attention in the current 30-day window.
- No segmented attention signals observed in the current window.
Bucketed signal based on recent segmented Verify telemetry. Crawler and evaluator activity is not treated as confirmed human demand.
Status
Healthy
Score
73.8
Transport
streamable-http
Tools
12
DISPUTE THIS ASSESSMENT
Dispute this assessment
If any published claim about this server -- its score, a risk flag, a capability classification, or its taxonomy -- is factually wrong, tell us what evidence shows and we will review it. This does not require claiming or verifying ownership of the server first.
Verify responds to disputes within 5 business days and resolves them within 15.
Dispute history
No disputes filed for this server.
Risk
Security posture
Tools analyzed
12
High-risk tools
1
Destructive tools
2
Exec tools
1
Egress tools
0
Secret tools
0
Bulk-access tools
0
Risk distribution
low:7, medium:4, high:1
Tool capability & risk inventory
| Tool | Capabilities | Risk | Findings | Notes |
|---|---|---|---|---|
whoami |
read | Low | none | No explicit safeguard hints detected. |
get_day |
read | Low | none | No explicit safeguard hints detected. |
get_range |
read | Low | none | No explicit safeguard hints detected. |
get_preferences |
read | Low | none | No explicit safeguard hints detected. |
log_meal |
undetermined | Low | none | No explicit safeguard hints detected. |
update_meal |
write | Medium | none | No explicit safeguard hints detected. |
delete_meal |
write delete | Medium | destructive operation | No explicit safeguard hints detected. |
get_pantry |
read | Low | none | No explicit safeguard hints detected. |
add_pantry_item |
write | Medium | none | No explicit safeguard hints detected. |
remove_pantry_item |
read write delete | Medium | destructive operation | No explicit safeguard hints detected. |
search_foods |
read exec | High | command execution freeform input surface | No explicit safeguard hints detected. |
lookup_barcode |
read | Low | none | No explicit safeguard hints detected. |
Write-action governance
Governance status
Warning
Safe to publish
Auth boundary
oauth_or_auth_required
Blast radius
Medium
High-risk tools
1
Confirmation signals
delete_meal
Safeguard count
0
Status detail: 1 high-risk tool(s), 2 destructive tool(s), 1 exec-capable tool(s); auth boundary is oauth or auth required with 0 safeguard(s) and 1 confirmation signal(s).
| Tool | Risk | Flags | Safeguards |
|---|---|---|---|
search_foods |
High | command execution freeform input surface | no |
Action-controls diff
Snapshot changed
yes
Disabled-by-default candidates
delete_meal remove_pantry_item search_foods
Manual review candidates
delete_meal remove_pantry_item search_foods
New actions
| Action | Risk | Flags |
|---|---|---|
add_pantry_item | Medium | none |
delete_meal | Medium | destructive operation |
get_day | Low | none |
get_pantry | Low | none |
get_preferences | Low | none |
get_range | Low | none |
log_meal | Low | none |
lookup_barcode | Low | none |
remove_pantry_item | Medium | destructive operation |
search_foods | High | command execution freeform input surface |
update_meal | Medium | none |
whoami | Low | none |
Changed actions
| Action | Change types | Risk |
|---|---|---|
| No materially changed actions. | ||
Critical alerts
Critical alerts
3
Production verdicts degrade quickly when critical alerts are active.
Compatibility
Client compatibility verdicts
Client compatibility only means the server shape can work with a client. Production trust decision and write-action publishing are evaluated separately so a client-compatible server can still be blocked for production.
Client compatibility: ChatGPT
Client-compatible
Transport compliance should be in good shape.
Confidence: high (77.5)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
initialize• OKtools_list• OKtransport_compliance_probe• Errorstep_up_auth_probe• Warningconnector_replay_probe• OK — Frozen tool snapshots must survive refresh.request_association_probe• Missing — Roots, sampling, and elicitation should stay request-scoped.
Client compatibility: Claude
Client-compatible
Transport behavior should match Claude-compatible HTTP expectations.
Confidence: high (77.5)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
initialize• OKtools_list• OKtransport_compliance_probe• Error
Write-action publishing
Publishing allowed
Current write surface is bounded enough for cautious review with production policy controls.
Confidence: high (77.5)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history
Disagreements: none
action_safety_probe• Warning
Snapshot churn risk
Medium
The live tool surface changed between recent validations.
Confidence: high (77.5)
Evidence provenance
Winner: history
Supporting sources: history, live_validation
Disagreements: none
tool_snapshot_probe• OKconnector_replay_probe• OK
Client compatibility gate details
ChatGPT custom connector
Client-compatible
Remediation checklist
Transport compliance should be in good shape.The tool surface is not limited to search/fetch-style read tools.This client profile expects a read/search-only tool surface, but write, delete, or exec-capable tools are present.A connector refresh would break existing tool references (new required arguments or removed tools) -- an admin must re-approve the connector before this is safe.Not yet safe for company-knowledge use: requires a search/fetch-only surface with no write actions present.Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.
Claude remote MCP
Client-compatible
Remediation checklist
Transport behavior should match Claude-compatible HTTP expectations.The tool surface is not limited to search/fetch-style read tools.This client profile expects a read/search-only tool surface, but write, delete, or exec-capable tools are present.A connector refresh would break existing tool references (new required arguments or removed tools) -- an admin must re-approve the connector before this is safe.Not yet safe for company-knowledge use: requires a search/fetch-only surface with no write actions present.Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.
Write-safe publishing
Ready
Remediation checklist
- No explicit blockers recorded.
Verdict traces
Production verdict
Safe for evaluation
The server is suitable for evaluation, but remaining gaps should be resolved before broad production use.
Confidence: high (77.5)
Winning source: live_validation
Triggering alerts
tool_snapshot_changed• high • Tool snapshot changedauth_mode_changed• high • Auth mode changedwrite_action_surface_expanded• high • Write-action surface expanded
Client verdict trace table
| Verdict | Status | Checks | Winning source | Conflicts |
|---|---|---|---|---|
openai_connectors |
Client-compatible | initialize, tools_list, transport_compliance_probe, step_up_auth_probe, connector_replay_probe, request_association_probe | live_validation | none |
claude_desktop |
Client-compatible | initialize, tools_list, transport_compliance_probe | live_validation | none |
unsafe_for_write_actions |
Publishing allowed | action_safety_probe | live_validation | none |
snapshot_churn_risk |
Medium | tool_snapshot_probe, connector_replay_probe | history | none |
Publishability policy profiles
ChatGPT custom connector compatibility
Compatible with review
Transport compliance should be in good shape. Compatibility is not a production approval; company knowledge and Messages API gates remain separate.
- Search Fetch Only: No
- Write Actions Present: Yes
- Oauth Configured: Yes
- Admin Refresh Required: Yes
- Safe For Company Knowledge: No
- Safe For Messages Api Remote Mcp: No
Claude remote MCP compatibility
Connector-compatible
Transport behavior should match Claude-compatible HTTP expectations. Compatibility is not a production approval; company knowledge and Messages API gates remain separate.
- Search Fetch Only: No
- Write Actions Present: Yes
- Oauth Configured: Yes
- Admin Refresh Required: Yes
- Safe For Company Knowledge: No
- Safe For Messages Api Remote Mcp: No
Compatibility fixtures
ChatGPT custom connector fixture
Passes
Transport compliance should be in good shape.
- remote_http_endpoint: Passes
- oauth_discovery: Passes
- frozen_tool_snapshot_refresh: Passes
- request_association: Passes
Anthropic remote MCP fixture
Degraded
Transport behavior should match Claude-compatible HTTP expectations.
- remote_transport: Passes
- tool_discovery: Passes
- auth_connect: Passes
- safe_write_review: Passes
Recommended for
OpenAI connectors
OpenAI connectors is marked compatible with score 89.
Claude Desktop
Claude Desktop is marked compatible with score 83.
Smithery
Smithery is marked compatible with score 80.
Generic Streamable HTTP
Generic Streamable HTTP is marked compatible with score 100.
Evidence
Current trust snapshot
Snapshot ID
trustsnap_bdffe6a1dc7e6fccUse this ID to compare server page, report, policy, MCP, homepage, ranking, and shortlist surfaces.
Snapshot generated
Aug 05, 2026 04:55:20 PM UTC
All page, report, policy, and MCP surfaces use this same server-detail snapshot shape.
Last validated
Aug 04, 2026 08:50:36 PM UTC
Age: 20.08h • evidence age tier: Verified in last 24h • display score: 73.82
Canonical machine links
Compare index
Compare API
Trust summary
Report JSON
Policy export
Badge metadata
Ledger evidence
Human compare URL
Evidence confidence
Confidence score
77.5
Based on 2 recent validations, 26 captured checks, and validation age of 20.1 hours.
Live checks captured
26
More direct checks increase trust in the current verdict.
Validation age
20.1h
Lower age means fresher evidence.
Latest validation evidence
Latest summary
Healthy
Validation profile
remote_mcp
Started
Aug 04, 2026 08:50:34 PM UTC
Latency
1599.1 ms
Failures
server_cardExpecting value: line 1 column 1 (char 0)transport_compliance_probeIssues: missing session id, missing protocol header, bad protocol not rejected (bad protocol=200).
Checks
| Check | Status | Latency | Evidence |
|---|---|---|---|
action_safety_probe |
Warning | n/a | 4 high-risk, 3 destructive, 1 exec-capable tool(s); auth present; safeguards=0; confirmation=delete meal. |
advanced_capabilities_probe |
Warning | n/a | Only 2 capability signal(s): prompts, resources. |
connector_publishability_probe |
Warning | n/a | Publishability blockers: transport compliance, server card. |
connector_replay_probe |
OK | n/a | Backward compatible with no breaking tool-surface changes. |
determinism_probe |
OK | 47.5 ms | Check completed |
initialize |
OK | 41.9 ms | Protocol 2025-06-18 |
interactive_flow_probe |
OK | n/a | Check completed |
oauth_authorization_server |
OK | 549.4 ms | authorization_endpoint, client_id_metadata_document_supported, code_challenge_methods_supported, device_authorization_endpoint |
oauth_protected_resource |
OK | 44.6 ms | 1 authorization server(s) |
official_registry_probe |
OK | n/a | Check completed |
openid_configuration |
OK | 149.4 ms | authorization_endpoint, device_authorization_endpoint, grant_types_supported, id_token_signing_alg_values_supported |
probe_noise_resilience |
OK | 41.6 ms | Fetched https://mcp.forkmate.ai/robots.txt |
prompt_get |
Missing | n/a | not advertised |
prompts_list |
OK | 47.1 ms | 0 prompt(s) exposed |
protocol_version_probe |
Warning | n/a | Claims 2025-06-18; 1 release(s) behind 2025-11-25. |
provenance_divergence_probe |
OK | n/a | Check completed |
request_association_probe |
Missing | n/a | No request-association capabilities were advertised. |
resource_read |
Missing | n/a | not advertised |
resources_list |
OK | 48.1 ms | 0 resource item(s) exposed |
server_card |
Error | 435.8 ms | Expecting value: line 1 column 1 (char 0) |
session_resume_probe |
Warning | n/a | no session id |
step_up_auth_probe |
Warning | n/a | Scopes=email, offline access, openid, profile. |
tool_snapshot_probe |
OK | n/a | Check completed |
tools_list |
OK | 43.8 ms | 12 tool(s) exposed |
transport_compliance_probe |
Error | 44.9 ms | Issues: missing session id, missing protocol header, bad protocol not rejected (bad protocol=200). |
utility_coverage_probe |
OK | 43.7 ms | No completions evidence; no pagination evidence; tasks auth required. |
Raw evidence view
Show raw JSON evidence
{
"checks": {
"action_safety_probe": {
"details": {
"auth_present": true,
"confirmation_signals": [
"delete_meal"
],
"safeguard_count": 0,
"summary": {
"bulk_access_tools": 1,
"capability_distribution": {
"admin": 12,
"delete": 3,
"exec": 1,
"export": 1,
"read": 11,
"write": 11
},
"destructive_tools": 3,
"egress_tools": 0,
"exec_tools": 1,
"high_risk_tools": 4,
"risk_distribution": {
"critical": 1,
"high": 3,
"low": 0,
"medium": 8
},
"secret_tools": 0,
"tool_count": 12
}
},
"latency_ms": null,
"status": "warning"
},
"advanced_capabilities_probe": {
"details": {
"capabilities": {
"completions": false,
"elicitation": false,
"prompts": true,
"resource_links": false,
"resources": true,
"roots": false,
"sampling": false,
"structured_outputs": false
},
"enabled": [
"prompts",
"resources"
],
"enabled_count": 2,
"initialize_capability_keys": [
"tools"
]
},
"latency_ms": null,
"status": "warning"
},
"connector_publishability_probe": {
"details": {
"blockers": [
"transport_compliance",
"server_card"
],
"criteria": {
"action_safety": true,
"auth_flow": true,
"connector_replay": true,
"initialize": true,
"protocol_version": true,
"remote_transport": true,
"request_association": true,
"server_card": false,
"session_resume": true,
"step_up_auth": true,
"tool_surface": true,
"tools_list": true,
"transport_compliance": false
},
"high_risk_tools": 4,
"tool_count": 12,
"transport": "streamable-http"
},
"latency_ms": null,
"status": "warning"
},
"connector_replay_probe": {
"details": {
"added_tools": [],
"additive_output_changes": [],
"backward_compatible": true,
"output_breaks": [],
"removed_tools": [],
"required_arg_breaks": [],
"would_break_after_refresh": false
},
"latency_ms": null,
"status": "ok"
},
"determinism_probe": {
"details": {
"attempts": 2,
"baseline_signature": "06d858e5c213ad2341e27a8b0a2f91e11d705c35ba5a908866502c22652bcb66",
"errors": [],
"matches": 2,
"stable_ratio": 1.0,
"successful": 2
},
"latency_ms": 47.55,
"status": "ok"
},
"initialize": {
"details": {
"headers": {
"content-type": "application/json",
"strict-transport-security": "max-age=63072000; includeSubDomains"
},
"http_status": 200,
"payload": {
"id": 1,
"jsonrpc": "2.0",
"result": {
"capabilities": {
"tools": {}
},
"protocolVersion": "2025-06-18",
"serverInfo": {
"name": "forkmate",
"version": "0.0.0"
}
}
},
"url": "https://mcp.forkmate.ai/"
},
"latency_ms": 41.9,
"status": "ok"
},
"interactive_flow_probe": {
"details": {
"oauth_supported": true,
"prompt_available": false,
"risk_hits": [],
"safe_hits": []
},
"latency_ms": null,
"status": "ok"
},
"oauth_authorization_server": {
"details": {
"headers": {
"content-type": "application/json; charset=utf-8",
"strict-transport-security": "max-age=31536000; includeSubDomains; preload"
},
"http_status": 200,
"payload": {
"authorization_endpoint": "https://flexible-thought-84.authkit.app/oauth2/authorize",
"client_id_metadata_document_supported": true,
"code_challenge_methods_supported": [
"S256"
],
"device_authorization_endpoint": "https://flexible-thought-84.authkit.app/oauth2/device_authorization",
"grant_types_supported": [
"authorization_code",
"refresh_token",
"urn:ietf:params:oauth:grant-type:device_code"
],
"introspection_endpoint": "https://flexible-thought-84.authkit.app/oauth2/introspection",
"issuer": "https://flexible-thought-84.authkit.app",
"jwks_uri": "https://flexible-thought-84.authkit.app/oauth2/jwks",
"registration_endpoint": "https://flexible-thought-84.authkit.app/oauth2/register",
"response_modes_supported": [
"query"
],
"response_types_supported": [
"code"
],
"scopes_supported": [
"email",
"offline_access",
"openid",
"profile"
],
"token_endpoint": "https://flexible-thought-84.authkit.app/oauth2/token",
"token_endpoint_auth_methods_supported": [
"none",
"client_secret_post",
"client_secret_basic"
]
},
"url": "https://flexible-thought-84.authkit.app/.well-known/oauth-authorization-server"
},
"latency_ms": 549.38,
"status": "ok"
},
"oauth_protected_resource": {
"details": {
"headers": {
"content-type": "application/json",
"strict-transport-security": "max-age=63072000; includeSubDomains"
},
"http_status": 200,
"payload": {
"authorization_servers": [
"https://flexible-thought-84.authkit.app"
],
"bearer_methods_supported": [
"header"
],
"resource": "https://mcp.forkmate.ai",
"scopes_supported": [
"openid",
"profile",
"email",
"offline_access"
]
},
"url": "https://mcp.forkmate.ai/.well-known/oauth-protected-resource"
},
"latency_ms": 44.58,
"status": "ok"
},
"official_registry_probe": {
"details": {
"direct_match": true,
"official_peer_count": 1,
"registry_identifier": "ai.forkmate/forkmate",
"registry_source": "official_registry"
},
"latency_ms": null,
"status": "ok"
},
"openid_configuration": {
"details": {
"headers": {
"content-type": "application/json; charset=utf-8",
"strict-transport-security": "max-age=31536000; includeSubDomains; preload"
},
"http_status": 200,
"payload": {
"authorization_endpoint": "https://flexible-thought-84.authkit.app/oauth2/authorize",
"device_authorization_endpoint": "https://flexible-thought-84.authkit.app/oauth2/device_authorization",
"grant_types_supported": [
"authorization_code",
"client_credentials",
"refresh_token",
"urn:ietf:params:oauth:grant-type:device_code"
],
"id_token_signing_alg_values_supported": [
"RS256"
],
"introspection_endpoint": "https://flexible-thought-84.authkit.app/oauth2/introspection",
"issuer": "https://flexible-thought-84.authkit.app",
"jwks_uri": "https://flexible-thought-84.authkit.app/oauth2/jwks",
"response_types_supported": [
"code"
],
"scopes_supported": [
"email",
"offline_access",
"openid",
"profile"
],
"subject_types_supported": [
"public"
],
"token_endpoint": "https://flexible-thought-84.authkit.app/oauth2/token",
"token_endpoint_auth_methods_supported": [
"none",
"client_secret_basic",
"client_secret_post"
],
"userinfo_endpoint": "https://flexible-thought-84.authkit.app/oauth2/userinfo"
},
"url": "https://flexible-thought-84.authkit.app/.well-known/openid-configuration"
},
"latency_ms": 149.44,
"status": "ok"
},
"probe_noise_resilience": {
"details": {
"headers": {
"content-type": "text/plain; charset=utf-8",
"strict-transport-security": "max-age=63072000; includeSubDomains"
},
"http_status": 200,
"url": "https://mcp.forkmate.ai/robots.txt"
},
"latency_ms": 41.62,
"status": "ok"
},
"prompt_get": {
"details": {
"reason": "not_advertised"
},
"latency_ms": null,
"status": "missing"
},
"prompts_list": {
"details": {
"headers": {
"content-type": "application/json",
"strict-transport-security": "max-age=63072000; includeSubDomains"
},
"http_status": 200,
"payload": {
"id": 3,
"jsonrpc": "2.0",
"result": {
"prompts": []
}
},
"url": "https://mcp.forkmate.ai/"
},
"latency_ms": 47.13,
"status": "ok"
},
"protocol_version_probe": {
"details": {
"claimed_version": "2025-06-18",
"lag_days": 160,
"latest_known_version": "2025-11-25",
"releases_behind": 1,
"validator_protocol_version": "2025-03-26"
},
"latency_ms": null,
"status": "warning"
},
"provenance_divergence_probe": {
"details": {
"direct_official_match": true,
"drift_fields": [],
"metadata_document_count": 2,
"registry_homepage": null,
"registry_repository": null,
"registry_title": null,
"registry_version": null,
"server_card_homepage": null,
"server_card_repository": null,
"server_card_title": null,
"server_card_version": null
},
"latency_ms": null,
"status": "ok"
},
"request_association_probe": {
"details": {
"reason": "no_request_association_capabilities_advertised"
},
"latency_ms": null,
"status": "missing"
},
"resource_read": {
"details": {
"reason": "not_advertised"
},
"latency_ms": null,
"status": "missing"
},
"resources_list": {
"details": {
"headers": {
"content-type": "application/json",
"strict-transport-security": "max-age=63072000; includeSubDomains"
},
"http_status": 200,
"payload": {
"id": 5,
"jsonrpc": "2.0",
"result": {
"resources": []
}
},
"url": "https://mcp.forkmate.ai/"
},
"latency_ms": 48.13,
"status": "ok"
},
"server_card": {
"details": {
"error": "Expecting value: line 1 column 1 (char 0)",
"url": "https://mcp.forkmate.ai/.well-known/mcp/server-card.json"
},
"latency_ms": 435.84,
"status": "error"
},
"session_resume_probe": {
"details": {
"protocol_version": "2025-06-18",
"reason": "no_session_id",
"resume_expected": true,
"transport": "streamable-http"
},
"latency_ms": null,
"status": "warning"
},
"step_up_auth_probe": {
"details": {
"auth_required_checks": [],
"broad_scopes": [],
"challenge_headers": [],
"minimal_scope_documented": false,
"oauth_present": true,
"scope_specificity_ratio": 0.2,
"step_up_signals": [],
"supported_scopes": [
"email",
"offline_access",
"openid",
"profile"
]
},
"latency_ms": null,
"status": "warning"
},
"tool_snapshot_probe": {
"details": {
"added": [],
"changed_outputs": [],
"current_tool_count": 12,
"previous_tool_count": 12,
"removed": [],
"similarity": 1.0
},
"latency_ms": null,
"status": "ok"
},
"tools_list": {
"details": {
"headers": {
"content-type": "application/json",
"strict-transport-security": "max-age=63072000; includeSubDomains"
},
"http_status": 200,
"payload": {
"id": 2,
"jsonrpc": "2.0",
"result": {
"tools": [
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Who am I"
},
"description": "Diagnostic: returns the authenticated user id and scopes.",
"inputSchema": {
"additionalProperties": false,
"properties": {},
"type": "object"
},
"name": "whoami"
},
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Get day's diary"
},
"description": "Read the user's food diary for a day (entries + calorie/macro totals). SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"local_date": {
"description": "YYYY-MM-DD; defaults to today.",
"type": "string"
}
},
"type": "object"
},
"name": "get_day"
},
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Get diary range"
},
"description": "Read the user's diary across a date range, with per-day calorie/macro totals. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"end": {
"description": "YYYY-MM-DD (inclusive).",
"type": "string"
},
"start": {
"description": "YYYY-MM-DD (inclusive).",
"type": "string"
}
},
"required": [
"start",
"end"
],
"type": "object"
},
"name": "get_range"
},
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Get dietary preferences"
},
"description": "Read the user's saved dietary preferences so you can tailor logging and suggestions WITHOUT re-asking every chat: their diet style, a structured list of allergies to avoid (the big-9 major allergens), foods they dislike, and a typical-portion note. IMPORTANT: the allergen list is self-reported and is NOT a safety guarantee \u2014 always tell the user to check ingredient labels themselves; cross-contamination and gaps in food data are not captured (see the returned allergy_disclaimer). The `allergies` field covers the major US allergens ONLY; a user may have an allergen outside it (e.g. mustard, celery, corn, mollusks, barley/rye) \u2014 ask about those directly. NEVER treat the `dislikes` list as an allergy: it is a taste preference to de-prioritize, never a safety exclusion.",
"inputSchema": {
"additionalProperties": false,
"properties": {},
"type": "object"
},
"name": "get_preferences"
},
{
"annotations": {
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Log a meal"
},
"description": "Log what the user ate to their food diary. Parse the user's free text into items and, when you can, include estimated macros per item for accuracy. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"at": {
"description": "ISO-8601 instant the meal was eaten; defaults to now.",
"type": "string"
},
"items": {
"items": {
"properties": {
"barcode": {
"type": "string"
},
"caffeine_mg": {
"description": "Optional caffeine content of this item, in milligrams (e.g. ~95 for a mug of brewed coffee). Include it for caffeinated drinks/foods when known; omit if unknown.",
"type": "number"
},
"fluid_ml": {
"description": "Optional fluid/hydration volume of this item, in millilitres (e.g. 240 for an 8 oz cup). Include it for drinks when known; omit if unknown.",
"type": "number"
},
"macros": {
"properties": {
"carb_g": {
"type": "number"
},
"fat_g": {
"type": "number"
},
"kcal": {
"type": "number"
},
"protein_g": {
"type": "number"
}
},
"type": "object"
},
"name": {
"type": "string"
},
"quantity": {
"description": "Portion as the user stated it, e.g. '3' or '1 cup'. When logging a search_foods/lookup_barcode candidate you scaled by its serving, write it as 'N \u00d7 <serving_label> (<total_g> g)' to match the web app's diary \u2014 e.g. a candidate with serving_grams 48 and serving_label '1 frank', eaten \u00d72, becomes macros = the per-100 g figures \u00d7 0.96 (96 g total), quantity '2 \u00d7 1 frank (96 g)', and `source` set to that candidate's source. This field is a DISPLAY LABEL ONLY \u2014 you must still send the already-scaled macros; the server never re-scales them.",
"type": "string"
}
},
"required": [
"name"
],
"type": "object"
},
"minItems": 1,
"type": "array"
},
"local_date": {
"description": "YYYY-MM-DD diary date; defaults to the user's local date (from their timezone). Pass this to log a meal on a different day.",
"type": "string"
},
"meal": {
"enum": [
"breakfast",
"lunch",
"dinner",
"snack",
"other"
],
"type": "string"
},
"note": {
"type": "string"
},
"source": {
"description": "Optional provenance for these items. After search_foods/lookup_barcode, pass the candidate's source class (e.g. 'usda' or 'off') so the diary shows it's grounded. Defaults to 'client' (your own estimate). Unrecognized values are recorded as 'client'.",
"enum": [
"client",
"usda",
"off",
"usda-index",
"mfp-import",
"manual",
"chain-menu"
],
"type": "string"
}
},
"required": [
"items"
],
"type": "object"
},
"name": "log_meal"
},
{
"annotations": {
"destructiveHint": false,
"idempotentHint": true,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Edit a logged food"
},
"description": "Correct a food already logged to the user's diary \u2014 fix a wrong calorie/macro value, quantity, or name, or move an entry to a different meal. Identify the entry by its `id` and `local_date` (both from get_day) and the food by its `item_index` within that entry's items[]. Only the fields you send change; the macros you send are MERGED onto the existing ones (so sending just `kcal` leaves protein/carb/fat as they were). This overwrites the value IN PLACE \u2014 there is no history of the previous value. Editing never moves an entry to another day (to do that, delete and re-log). SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"caffeine_mg": {
"description": "Corrected caffeine content, in milligrams.",
"type": "number"
},
"fluid_ml": {
"description": "Corrected fluid/hydration volume, in millilitres.",
"type": "number"
},
"id": {
"description": "The entry id to edit (from get_day).",
"type": "string"
},
"item_index": {
"description": "Which food in the entry's items[] to edit (0-based). Required when changing a food's name/quantity/macros/caffeine/fluid; omit for an entry-level change (meal/note).",
"type": "number"
},
"local_date": {
"description": "YYYY-MM-DD diary date of the entry (from get_day).",
"type": "string"
},
"macros": {
"description": "Corrected macros \u2014 only the components you send are changed.",
"properties": {
"carb_g": {
"type": "number"
},
"fat_g": {
"type": "number"
},
"kcal": {
"type": "number"
},
"protein_g": {
"type": "number"
}
},
"type": "object"
},
"meal": {
"description": "Move the entry to a different meal label.",
"enum": [
"breakfast",
"lunch",
"dinner",
"snack",
"other"
],
"type": "string"
},
"name": {
"type": "string"
},
"note": {
"type": "string"
},
"quantity": {
"description": "Portion as stated, e.g. '2' or '1 cup'.",
"type": "string"
}
},
"required": [
"id",
"local_date"
],
"type": "object"
},
"name": "update_meal"
},
{
"annotations": {
"destructiveHint": true,
"idempotentHint": true,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Delete a logged food"
},
"description": "Delete a food from the user's diary \u2014 remove one food from an entry (by `item_index`), or the whole entry (omit `item_index`). Identify the entry by its `id` and `local_date` (both from get_day). This is a TRUE removal: the data is gone, with NO server-side tombstone and no undo. Deleting the last food in an entry removes the entry. Safe to retry \u2014 deleting something already gone is a no-op success. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"id": {
"description": "The entry id to delete from (from get_day).",
"type": "string"
},
"item_index": {
"description": "Which food to remove (0-based). Omit to delete the whole entry.",
"type": "number"
},
"local_date": {
"description": "YYYY-MM-DD diary date of the entry (from get_day).",
"type": "string"
}
},
"required": [
"id",
"local_date"
],
"type": "object"
},
"name": "delete_meal"
},
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Get pantry"
},
"description": "Read the user's PANTRY \u2014 the foods they keep ON HAND (their staples), so you can suggest meals from what they actually have and pre-fill macros when they log one. Returns each item's name and, when the user saved them, macros (for the item's serving), a serving label, a `source`, and a short note. The pantry is the user's CURATED list of what they stock \u2014 separate from what they've logged (their diary) and from their frequents (what they log often). IMPORTANT: a `source` (e.g. 'usda') is the user's own CLAIM about where the macros came from, NOT a server-verified guarantee \u2014 treat it as a hint, never as certified.",
"inputSchema": {
"additionalProperties": false,
"properties": {},
"type": "object"
},
"name": "get_pantry"
},
{
"annotations": {
"destructiveHint": false,
"idempotentHint": true,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Add or update a pantry item"
},
"description": "Add a food to the user's pantry, or UPDATE it if it's already there (matched by name, any casing) \u2014 e.g. 'add rolled oats to my pantry'. Only `name` is required; include `macros` (for one serving), a `serving` label, a `source`, and a short `note` when you know them, so a later log can reuse them. Re-adding the same food REPLACES its details (an upsert \u2014 it never creates a duplicate). Only pass a `source` you actually got from search_foods/lookup_barcode; an unrecognized value is recorded as the user's own estimate ('client'). This does NOT log a meal \u2014 it only curates the user's staples.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"macros": {
"description": "Macros for ONE serving of this food, when known.",
"properties": {
"carb_g": {
"type": "number"
},
"fat_g": {
"type": "number"
},
"kcal": {
"type": "number"
},
"protein_g": {
"type": "number"
}
},
"type": "object"
},
"name": {
"description": "The food to keep on hand, e.g. 'rolled oats'.",
"type": "string"
},
"note": {
"description": "Optional short note, e.g. 'the Costco tub'.",
"type": "string"
},
"serving": {
"description": "Serving label the macros are for, e.g. '1 cup' or 'per 100 g'.",
"type": "string"
},
"source": {
"description": "Where the macros came from, if grounded via search_foods/lookup_barcode (e.g. 'usda'). Defaults to your own estimate ('client'); unrecognized values are recorded as 'client'.",
"enum": [
"client",
"usda",
"off",
"usda-index",
"mfp-import",
"manual",
"chain-menu"
],
"type": "string"
}
},
"required": [
"name"
],
"type": "object"
},
"name": "add_pantry_item"
},
{
"annotations": {
"destructiveHint": true,
"idempotentHint": true,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Remove a pantry item"
},
"description": "Remove a food from the user's pantry by name \u2014 e.g. 'take eggs off my pantry list'. This removes it from their on-hand STAPLES only; it does NOT delete anything from their food diary. Safe to retry \u2014 removing something that isn't in the pantry is a no-op success.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"name": {
"description": "The food to remove from the pantry (any casing).",
"type": "string"
}
},
"required": [
"name"
],
"type": "object"
},
"name": "remove_pantry_item"
},
{
"annotations": {
"openWorldHint": true,
"readOnlyHint": true,
"title": "Search foods"
},
"description": "Search USDA FoodData Central and Open Food Facts for foods matching a query, returning candidates with macros and a `source` you can show the user. IMPORTANT: the macros are PER 100 g (see each candidate's `serving`) \u2014 scale them to the portion the user actually ate before logging with log_meal. A candidate MAY also carry `serving_grams`/`serving_label` for ONE household serving (e.g. 48 g / \"1 frank\") \u2014 when present, offer the user 'N servings' instead of asking for grams, but still scale the per-100 g macros to the resolved grams before logging. When you log a chosen candidate, pass its `source` to log_meal so the diary records real provenance (USDA/Open Food Facts) instead of an estimate. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"limit": {
"description": "Max candidates to return (default 5, clamped to 1\u201310).",
"type": "number"
},
"query": {
"description": "Food to search, e.g. 'greek yogurt' or 'Chipotle chicken'.",
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "search_foods"
},
{
"annotations": {
"openWorldHint": true,
"readOnlyHint": true,
"title": "Look up barcode"
},
"description": "Look up a packaged food by its UPC/EAN barcode via Open Food Facts. IMPORTANT: the macros are PER 100 g (see `serving`) \u2014 scale to the portion eaten before logging with log_meal. It MAY also carry `serving_grams`/`serving_label` for one household serving \u2014 offer 'N servings' when present, still scaling the per-100 g macros before logging. Pass the returned `source` to log_meal to preserve provenance. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"upc": {
"description": "UPC/EAN barcode, digits only (8\u201314 digits).",
"type": "string"
}
},
"required": [
"upc"
],
"type": "object"
},
"name": "lookup_barcode"
}
]
}
},
"url": "https://mcp.forkmate.ai/"
},
"latency_ms": 43.76,
"status": "ok"
},
"transport_compliance_probe": {
"details": {
"bad_protocol_error": null,
"bad_protocol_headers": {
"content-type": "application/json",
"strict-transport-security": "max-age=63072000; includeSubDomains"
},
"bad_protocol_payload": {
"id": 410,
"jsonrpc": "2.0",
"result": {
"tools": [
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Who am I"
},
"description": "Diagnostic: returns the authenticated user id and scopes.",
"inputSchema": {
"additionalProperties": false,
"properties": {},
"type": "object"
},
"name": "whoami"
},
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Get day's diary"
},
"description": "Read the user's food diary for a day (entries + calorie/macro totals). SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"local_date": {
"description": "YYYY-MM-DD; defaults to today.",
"type": "string"
}
},
"type": "object"
},
"name": "get_day"
},
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Get diary range"
},
"description": "Read the user's diary across a date range, with per-day calorie/macro totals. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"end": {
"description": "YYYY-MM-DD (inclusive).",
"type": "string"
},
"start": {
"description": "YYYY-MM-DD (inclusive).",
"type": "string"
}
},
"required": [
"start",
"end"
],
"type": "object"
},
"name": "get_range"
},
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Get dietary preferences"
},
"description": "Read the user's saved dietary preferences so you can tailor logging and suggestions WITHOUT re-asking every chat: their diet style, a structured list of allergies to avoid (the big-9 major allergens), foods they dislike, and a typical-portion note. IMPORTANT: the allergen list is self-reported and is NOT a safety guarantee \u2014 always tell the user to check ingredient labels themselves; cross-contamination and gaps in food data are not captured (see the returned allergy_disclaimer). The `allergies` field covers the major US allergens ONLY; a user may have an allergen outside it (e.g. mustard, celery, corn, mollusks, barley/rye) \u2014 ask about those directly. NEVER treat the `dislikes` list as an allergy: it is a taste preference to de-prioritize, never a safety exclusion.",
"inputSchema": {
"additionalProperties": false,
"properties": {},
"type": "object"
},
"name": "get_preferences"
},
{
"annotations": {
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Log a meal"
},
"description": "Log what the user ate to their food diary. Parse the user's free text into items and, when you can, include estimated macros per item for accuracy. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"at": {
"description": "ISO-8601 instant the meal was eaten; defaults to now.",
"type": "string"
},
"items": {
"items": {
"properties": {
"barcode": {
"type": "string"
},
"caffeine_mg": {
"description": "Optional caffeine content of this item, in milligrams (e.g. ~95 for a mug of brewed coffee). Include it for caffeinated drinks/foods when known; omit if unknown.",
"type": "number"
},
"fluid_ml": {
"description": "Optional fluid/hydration volume of this item, in millilitres (e.g. 240 for an 8 oz cup). Include it for drinks when known; omit if unknown.",
"type": "number"
},
"macros": {
"properties": {
"carb_g": {
"type": "number"
},
"fat_g": {
"type": "number"
},
"kcal": {
"type": "number"
},
"protein_g": {
"type": "number"
}
},
"type": "object"
},
"name": {
"type": "string"
},
"quantity": {
"description": "Portion as the user stated it, e.g. '3' or '1 cup'. When logging a search_foods/lookup_barcode candidate you scaled by its serving, write it as 'N \u00d7 <serving_label> (<total_g> g)' to match the web app's diary \u2014 e.g. a candidate with serving_grams 48 and serving_label '1 frank', eaten \u00d72, becomes macros = the per-100 g figures \u00d7 0.96 (96 g total), quantity '2 \u00d7 1 frank (96 g)', and `source` set to that candidate's source. This field is a DISPLAY LABEL ONLY \u2014 you must still send the already-scaled macros; the server never re-scales them.",
"type": "string"
}
},
"required": [
"name"
],
"type": "object"
},
"minItems": 1,
"type": "array"
},
"local_date": {
"description": "YYYY-MM-DD diary date; defaults to the user's local date (from their timezone). Pass this to log a meal on a different day.",
"type": "string"
},
"meal": {
"enum": [
"breakfast",
"lunch",
"dinner",
"snack",
"other"
],
"type": "string"
},
"note": {
"type": "string"
},
"source": {
"description": "Optional provenance for these items. After search_foods/lookup_barcode, pass the candidate's source class (e.g. 'usda' or 'off') so the diary shows it's grounded. Defaults to 'client' (your own estimate). Unrecognized values are recorded as 'client'.",
"enum": [
"client",
"usda",
"off",
"usda-index",
"mfp-import",
"manual",
"chain-menu"
],
"type": "string"
}
},
"required": [
"items"
],
"type": "object"
},
"name": "log_meal"
},
{
"annotations": {
"destructiveHint": false,
"idempotentHint": true,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Edit a logged food"
},
"description": "Correct a food already logged to the user's diary \u2014 fix a wrong calorie/macro value, quantity, or name, or move an entry to a different meal. Identify the entry by its `id` and `local_date` (both from get_day) and the food by its `item_index` within that entry's items[]. Only the fields you send change; the macros you send are MERGED onto the existing ones (so sending just `kcal` leaves protein/carb/fat as they were). This overwrites the value IN PLACE \u2014 there is no history of the previous value. Editing never moves an entry to another day (to do that, delete and re-log). SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"caffeine_mg": {
"description": "Corrected caffeine content, in milligrams.",
"type": "number"
},
"fluid_ml": {
"description": "Corrected fluid/hydration volume, in millilitres.",
"type": "number"
},
"id": {
"description": "The entry id to edit (from get_day).",
"type": "string"
},
"item_index": {
"description": "Which food in the entry's items[] to edit (0-based). Required when changing a food's name/quantity/macros/caffeine/fluid; omit for an entry-level change (meal/note).",
"type": "number"
},
"local_date": {
"description": "YYYY-MM-DD diary date of the entry (from get_day).",
"type": "string"
},
"macros": {
"description": "Corrected macros \u2014 only the components you send are changed.",
"properties": {
"carb_g": {
"type": "number"
},
"fat_g": {
"type": "number"
},
"kcal": {
"type": "number"
},
"protein_g": {
"type": "number"
}
},
"type": "object"
},
"meal": {
"description": "Move the entry to a different meal label.",
"enum": [
"breakfast",
"lunch",
"dinner",
"snack",
"other"
],
"type": "string"
},
"name": {
"type": "string"
},
"note": {
"type": "string"
},
"quantity": {
"description": "Portion as stated, e.g. '2' or '1 cup'.",
"type": "string"
}
},
"required": [
"id",
"local_date"
],
"type": "object"
},
"name": "update_meal"
},
{
"annotations": {
"destructiveHint": true,
"idempotentHint": true,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Delete a logged food"
},
"description": "Delete a food from the user's diary \u2014 remove one food from an entry (by `item_index`), or the whole entry (omit `item_index`). Identify the entry by its `id` and `local_date` (both from get_day). This is a TRUE removal: the data is gone, with NO server-side tombstone and no undo. Deleting the last food in an entry removes the entry. Safe to retry \u2014 deleting something already gone is a no-op success. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"id": {
"description": "The entry id to delete from (from get_day).",
"type": "string"
},
"item_index": {
"description": "Which food to remove (0-based). Omit to delete the whole entry.",
"type": "number"
},
"local_date": {
"description": "YYYY-MM-DD diary date of the entry (from get_day).",
"type": "string"
}
},
"required": [
"id",
"local_date"
],
"type": "object"
},
"name": "delete_meal"
},
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Get pantry"
},
"description": "Read the user's PANTRY \u2014 the foods they keep ON HAND (their staples), so you can suggest meals from what they actually have and pre-fill macros when they log one. Returns each item's name and, when the user saved them, macros (for the item's serving), a serving label, a `source`, and a short note. The pantry is the user's CURATED list of what they stock \u2014 separate from what they've logged (their diary) and from their frequents (what they log often). IMPORTANT: a `source` (e.g. 'usda') is the user's own CLAIM about where the macros came from, NOT a server-verified guarantee \u2014 treat it as a hint, never as certified.",
"inputSchema": {
"additionalProperties": false,
"properties": {},
"type": "object"
},
"name": "get_pantry"
},
{
"annotations": {
"destructiveHint": false,
"idempotentHint": true,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Add or update a pantry item"
},
"description": "Add a food to the user's pantry, or UPDATE it if it's already there (matched by name, any casing) \u2014 e.g. 'add rolled oats to my pantry'. Only `name` is required; include `macros` (for one serving), a `serving` label, a `source`, and a short `note` when you know them, so a later log can reuse them. Re-adding the same food REPLACES its details (an upsert \u2014 it never creates a duplicate). Only pass a `source` you actually got from search_foods/lookup_barcode; an unrecognized value is recorded as the user's own estimate ('client'). This does NOT log a meal \u2014 it only curates the user's staples.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"macros": {
"description": "Macros for ONE serving of this food, when known.",
"properties": {
"carb_g": {
"type": "number"
},
"fat_g": {
"type": "number"
},
"kcal": {
"type": "number"
},
"protein_g": {
"type": "number"
}
},
"type": "object"
},
"name": {
"description": "The food to keep on hand, e.g. 'rolled oats'.",
"type": "string"
},
"note": {
"description": "Optional short note, e.g. 'the Costco tub'.",
"type": "string"
},
"serving": {
"description": "Serving label the macros are for, e.g. '1 cup' or 'per 100 g'.",
"type": "string"
},
"source": {
"description": "Where the macros came from, if grounded via search_foods/lookup_barcode (e.g. 'usda'). Defaults to your own estimate ('client'); unrecognized values are recorded as 'client'.",
"enum": [
"client",
"usda",
"off",
"usda-index",
"mfp-import",
"manual",
"chain-menu"
],
"type": "string"
}
},
"required": [
"name"
],
"type": "object"
},
"name": "add_pantry_item"
},
{
"annotations": {
"destructiveHint": true,
"idempotentHint": true,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Remove a pantry item"
},
"description": "Remove a food from the user's pantry by name \u2014 e.g. 'take eggs off my pantry list'. This removes it from their on-hand STAPLES only; it does NOT delete anything from their food diary. Safe to retry \u2014 removing something that isn't in the pantry is a no-op success.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"name": {
"description": "The food to remove from the pantry (any casing).",
"type": "string"
}
},
"required": [
"name"
],
"type": "object"
},
"name": "remove_pantry_item"
},
{
"annotations": {
"openWorldHint": true,
"readOnlyHint": true,
"title": "Search foods"
},
"description": "Search USDA FoodData Central and Open Food Facts for foods matching a query, returning candidates with macros and a `source` you can show the user. IMPORTANT: the macros are PER 100 g (see each candidate's `serving`) \u2014 scale them to the portion the user actually ate before logging with log_meal. A candidate MAY also carry `serving_grams`/`serving_label` for ONE household serving (e.g. 48 g / \"1 frank\") \u2014 when present, offer the user 'N servings' instead of asking for grams, but still scale the per-100 g macros to the resolved grams before logging. When you log a chosen candidate, pass its `source` to log_meal so the diary records real provenance (USDA/Open Food Facts) instead of an estimate. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"limit": {
"description": "Max candidates to return (default 5, clamped to 1\u201310).",
"type": "number"
},
"query": {
"description": "Food to search, e.g. 'greek yogurt' or 'Chipotle chicken'.",
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "search_foods"
},
{
"annotations": {
"openWorldHint": true,
"readOnlyHint": true,
"title": "Look up barcode"
},
"description": "Look up a packaged food by its UPC/EAN barcode via Open Food Facts. IMPORTANT: the macros are PER 100 g (see `serving`) \u2014 scale to the portion eaten before logging with log_meal. It MAY also carry `serving_grams`/`serving_label` for one household serving \u2014 offer 'N servings' when present, still scaling the per-100 g macros before logging. Pass the returned `source` to log_meal to preserve provenance. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"upc": {
"description": "UPC/EAN barcode, digits only (8\u201314 digits).",
"type": "string"
}
},
"required": [
"upc"
],
"type": "object"
},
"name": "lookup_barcode"
}
]
}
},
"bad_protocol_status_code": 200,
"delete_error": null,
"delete_status_code": null,
"expired_session_error": null,
"expired_session_status_code": null,
"issues": [
"missing_session_id",
"missing_protocol_header",
"bad_protocol_not_rejected"
],
"last_event_id_visible": false,
"protocol_header_present": false,
"requested_protocol_version": "2025-06-18",
"session_id_present": false,
"transport": "streamable-http"
},
"latency_ms": 44.9,
"status": "error"
},
"utility_coverage_probe": {
"details": {
"completions": {
"advertised": false,
"live_probe": "not_executed",
"sample_target": null
},
"initialize_capability_keys": [
"tools"
],
"pagination": {
"metadata_signal": false,
"next_cursor_methods": [],
"supported": false
},
"tasks": {
"advertised": false,
"http_status": 401,
"probe_status": "auth_required"
}
},
"latency_ms": 43.67,
"status": "ok"
}
},
"failures": {
"server_card": {
"error": "Expecting value: line 1 column 1 (char 0)",
"url": "https://mcp.forkmate.ai/.well-known/mcp/server-card.json"
},
"transport_compliance_probe": {
"bad_protocol_error": null,
"bad_protocol_headers": {
"content-type": "application/json",
"strict-transport-security": "max-age=63072000; includeSubDomains"
},
"bad_protocol_payload": {
"id": 410,
"jsonrpc": "2.0",
"result": {
"tools": [
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Who am I"
},
"description": "Diagnostic: returns the authenticated user id and scopes.",
"inputSchema": {
"additionalProperties": false,
"properties": {},
"type": "object"
},
"name": "whoami"
},
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Get day's diary"
},
"description": "Read the user's food diary for a day (entries + calorie/macro totals). SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"local_date": {
"description": "YYYY-MM-DD; defaults to today.",
"type": "string"
}
},
"type": "object"
},
"name": "get_day"
},
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Get diary range"
},
"description": "Read the user's diary across a date range, with per-day calorie/macro totals. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"end": {
"description": "YYYY-MM-DD (inclusive).",
"type": "string"
},
"start": {
"description": "YYYY-MM-DD (inclusive).",
"type": "string"
}
},
"required": [
"start",
"end"
],
"type": "object"
},
"name": "get_range"
},
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Get dietary preferences"
},
"description": "Read the user's saved dietary preferences so you can tailor logging and suggestions WITHOUT re-asking every chat: their diet style, a structured list of allergies to avoid (the big-9 major allergens), foods they dislike, and a typical-portion note. IMPORTANT: the allergen list is self-reported and is NOT a safety guarantee \u2014 always tell the user to check ingredient labels themselves; cross-contamination and gaps in food data are not captured (see the returned allergy_disclaimer). The `allergies` field covers the major US allergens ONLY; a user may have an allergen outside it (e.g. mustard, celery, corn, mollusks, barley/rye) \u2014 ask about those directly. NEVER treat the `dislikes` list as an allergy: it is a taste preference to de-prioritize, never a safety exclusion.",
"inputSchema": {
"additionalProperties": false,
"properties": {},
"type": "object"
},
"name": "get_preferences"
},
{
"annotations": {
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Log a meal"
},
"description": "Log what the user ate to their food diary. Parse the user's free text into items and, when you can, include estimated macros per item for accuracy. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"at": {
"description": "ISO-8601 instant the meal was eaten; defaults to now.",
"type": "string"
},
"items": {
"items": {
"properties": {
"barcode": {
"type": "string"
},
"caffeine_mg": {
"description": "Optional caffeine content of this item, in milligrams (e.g. ~95 for a mug of brewed coffee). Include it for caffeinated drinks/foods when known; omit if unknown.",
"type": "number"
},
"fluid_ml": {
"description": "Optional fluid/hydration volume of this item, in millilitres (e.g. 240 for an 8 oz cup). Include it for drinks when known; omit if unknown.",
"type": "number"
},
"macros": {
"properties": {
"carb_g": {
"type": "number"
},
"fat_g": {
"type": "number"
},
"kcal": {
"type": "number"
},
"protein_g": {
"type": "number"
}
},
"type": "object"
},
"name": {
"type": "string"
},
"quantity": {
"description": "Portion as the user stated it, e.g. '3' or '1 cup'. When logging a search_foods/lookup_barcode candidate you scaled by its serving, write it as 'N \u00d7 <serving_label> (<total_g> g)' to match the web app's diary \u2014 e.g. a candidate with serving_grams 48 and serving_label '1 frank', eaten \u00d72, becomes macros = the per-100 g figures \u00d7 0.96 (96 g total), quantity '2 \u00d7 1 frank (96 g)', and `source` set to that candidate's source. This field is a DISPLAY LABEL ONLY \u2014 you must still send the already-scaled macros; the server never re-scales them.",
"type": "string"
}
},
"required": [
"name"
],
"type": "object"
},
"minItems": 1,
"type": "array"
},
"local_date": {
"description": "YYYY-MM-DD diary date; defaults to the user's local date (from their timezone). Pass this to log a meal on a different day.",
"type": "string"
},
"meal": {
"enum": [
"breakfast",
"lunch",
"dinner",
"snack",
"other"
],
"type": "string"
},
"note": {
"type": "string"
},
"source": {
"description": "Optional provenance for these items. After search_foods/lookup_barcode, pass the candidate's source class (e.g. 'usda' or 'off') so the diary shows it's grounded. Defaults to 'client' (your own estimate). Unrecognized values are recorded as 'client'.",
"enum": [
"client",
"usda",
"off",
"usda-index",
"mfp-import",
"manual",
"chain-menu"
],
"type": "string"
}
},
"required": [
"items"
],
"type": "object"
},
"name": "log_meal"
},
{
"annotations": {
"destructiveHint": false,
"idempotentHint": true,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Edit a logged food"
},
"description": "Correct a food already logged to the user's diary \u2014 fix a wrong calorie/macro value, quantity, or name, or move an entry to a different meal. Identify the entry by its `id` and `local_date` (both from get_day) and the food by its `item_index` within that entry's items[]. Only the fields you send change; the macros you send are MERGED onto the existing ones (so sending just `kcal` leaves protein/carb/fat as they were). This overwrites the value IN PLACE \u2014 there is no history of the previous value. Editing never moves an entry to another day (to do that, delete and re-log). SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"caffeine_mg": {
"description": "Corrected caffeine content, in milligrams.",
"type": "number"
},
"fluid_ml": {
"description": "Corrected fluid/hydration volume, in millilitres.",
"type": "number"
},
"id": {
"description": "The entry id to edit (from get_day).",
"type": "string"
},
"item_index": {
"description": "Which food in the entry's items[] to edit (0-based). Required when changing a food's name/quantity/macros/caffeine/fluid; omit for an entry-level change (meal/note).",
"type": "number"
},
"local_date": {
"description": "YYYY-MM-DD diary date of the entry (from get_day).",
"type": "string"
},
"macros": {
"description": "Corrected macros \u2014 only the components you send are changed.",
"properties": {
"carb_g": {
"type": "number"
},
"fat_g": {
"type": "number"
},
"kcal": {
"type": "number"
},
"protein_g": {
"type": "number"
}
},
"type": "object"
},
"meal": {
"description": "Move the entry to a different meal label.",
"enum": [
"breakfast",
"lunch",
"dinner",
"snack",
"other"
],
"type": "string"
},
"name": {
"type": "string"
},
"note": {
"type": "string"
},
"quantity": {
"description": "Portion as stated, e.g. '2' or '1 cup'.",
"type": "string"
}
},
"required": [
"id",
"local_date"
],
"type": "object"
},
"name": "update_meal"
},
{
"annotations": {
"destructiveHint": true,
"idempotentHint": true,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Delete a logged food"
},
"description": "Delete a food from the user's diary \u2014 remove one food from an entry (by `item_index`), or the whole entry (omit `item_index`). Identify the entry by its `id` and `local_date` (both from get_day). This is a TRUE removal: the data is gone, with NO server-side tombstone and no undo. Deleting the last food in an entry removes the entry. Safe to retry \u2014 deleting something already gone is a no-op success. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"properties": {
"id": {
"description": "The entry id to delete from (from get_day).",
"type": "string"
},
"item_index": {
"description": "Which food to remove (0-based). Omit to delete the whole entry.",
"type": "number"
},
"local_date": {
"description": "YYYY-MM-DD diary date of the entry (from get_day).",
"type": "string"
}
},
"required": [
"id",
"local_date"
],
"type": "object"
},
"name": "delete_meal"
},
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true,
"title": "Get pantry"
},
"description": "Read the user's PANTRY \u2014 the foods they keep ON HAND (their staples), so you can suggest meals from what they actually have and pre-fill macros when they log one. Returns each item's name and, when the user saved them, macros (for the item's serving), a serving label, a `source`, and a short note. The pantry is the user's CURATED list of what they stock \u2014 separate from what they've logged (their diary) and from their frequents (what they log often). IMPORTANT: a `source` (e.g. 'usda') is the user's own CLAIM about where the macros came from, NOT a server-verified guarantee \u2014 treat it as a hint, never as certified.",
"inputSchema": {
"additionalProperties": false,
"properties": {},
"type": "object"
},
"name": "get_pantry"
},
{
"annotations": {
"destructiveHint": false,
"idempotentHint": true,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Add or update a pantry item"
},
"description": "Add a food to the user's pantry, or UPDATE it if it's already there (matched by name, any casing) \u2014 e.g. 'add rolled oats to my pantry'. Only `name` is required; include `macros` (for one serving), a `serving` label, a `source`, and a short `note` when you know them, so a later log can reuse them. Re-adding the same food REPLACES its details (an upsert \u2014 it never creates a duplicate). Only pass a `source` you actually got from search_foods/lookup_barcode; an unrecognized value is recorded as the user's own estimate ('client'). This does NOT log a meal \u2014 it only curates the user's staples.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"macros": {
"description": "Macros for ONE serving of this food, when known.",
"properties": {
"carb_g": {
"type": "number"
},
"fat_g": {
"type": "number"
},
"kcal": {
"type": "number"
},
"protein_g": {
"type": "number"
}
},
"type": "object"
},
"name": {
"description": "The food to keep on hand, e.g. 'rolled oats'.",
"type": "string"
},
"note": {
"description": "Optional short note, e.g. 'the Costco tub'.",
"type": "string"
},
"serving": {
"description": "Serving label the macros are for, e.g. '1 cup' or 'per 100 g'.",
"type": "string"
},
"source": {
"description": "Where the macros came from, if grounded via search_foods/lookup_barcode (e.g. 'usda'). Defaults to your own estimate ('client'); unrecognized values are recorded as 'client'.",
"enum": [
"client",
"usda",
"off",
"usda-index",
"mfp-import",
"manual",
"chain-menu"
],
"type": "string"
}
},
"required": [
"name"
],
"type": "object"
},
"name": "add_pantry_item"
},
{
"annotations": {
"destructiveHint": true,
"idempotentHint": true,
"openWorldHint": false,
"readOnlyHint": false,
"title": "Remove a pantry item"
},
"description": "Remove a food from the user's pantry by name \u2014 e.g. 'take eggs off my pantry list'. This removes it from their on-hand STAPLES only; it does NOT delete anything from their food diary. Safe to retry \u2014 removing something that isn't in the pantry is a no-op success.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"name": {
"description": "The food to remove from the pantry (any casing).",
"type": "string"
}
},
"required": [
"name"
],
"type": "object"
},
"name": "remove_pantry_item"
},
{
"annotations": {
"openWorldHint": true,
"readOnlyHint": true,
"title": "Search foods"
},
"description": "Search USDA FoodData Central and Open Food Facts for foods matching a query, returning candidates with macros and a `source` you can show the user. IMPORTANT: the macros are PER 100 g (see each candidate's `serving`) \u2014 scale them to the portion the user actually ate before logging with log_meal. A candidate MAY also carry `serving_grams`/`serving_label` for ONE household serving (e.g. 48 g / \"1 frank\") \u2014 when present, offer the user 'N servings' instead of asking for grams, but still scale the per-100 g macros to the resolved grams before logging. When you log a chosen candidate, pass its `source` to log_meal so the diary records real provenance (USDA/Open Food Facts) instead of an estimate. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"limit": {
"description": "Max candidates to return (default 5, clamped to 1\u201310).",
"type": "number"
},
"query": {
"description": "Food to search, e.g. 'greek yogurt' or 'Chipotle chicken'.",
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "search_foods"
},
{
"annotations": {
"openWorldHint": true,
"readOnlyHint": true,
"title": "Look up barcode"
},
"description": "Look up a packaged food by its UPC/EAN barcode via Open Food Facts. IMPORTANT: the macros are PER 100 g (see `serving`) \u2014 scale to the portion eaten before logging with log_meal. It MAY also carry `serving_grams`/`serving_label` for one household serving \u2014 offer 'N servings' when present, still scaling the per-100 g macros before logging. Pass the returned `source` to log_meal to preserve provenance. SAFETY: all calorie and macro values here \u2014 including carbohydrates \u2014 are ESTIMATES (from USDA / Open Food Facts or the user's own entry), approximate and not lab-measured or per-batch. They are for general nutrition tracking ONLY. Do NOT use them for insulin dosing, carb-counting for a bolus, blood-glucose prediction, or any other medical decision, and do NOT compute a dose or glucose estimate from them. For anything medical, direct the user to the product's own label and their care team.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"upc": {
"description": "UPC/EAN barcode, digits only (8\u201314 digits).",
"type": "string"
}
},
"required": [
"upc"
],
"type": "object"
},
"name": "lookup_barcode"
}
]
}
},
"bad_protocol_status_code": 200,
"delete_error": null,
"delete_status_code": null,
"expired_session_error": null,
"expired_session_status_code": null,
"issues": [
"missing_session_id",
"missing_protocol_header",
"bad_protocol_not_rejected"
],
"last_event_id_visible": false,
"protocol_header_present": false,
"requested_protocol_version": "2025-06-18",
"session_id_present": false,
"transport": "streamable-http"
}
},
"remote_url": "https://mcp.forkmate.ai/",
"server_card_payload": null,
"server_identifier": "ai.forkmate/forkmate"
}
Known versions
0.1.3
Validation history
7 day score delta
n/a
30 day score delta
n/a
Recent healthy ratio
100%
Freshness
20.1h
| Timestamp | Status | Score | Latency | Tools |
|---|---|---|---|---|
| Aug 04, 2026 08:50:36 PM UTC | Healthy | 73.8 | 1599.1 ms | 12 |
| Jul 31, 2026 06:37:41 AM UTC | Healthy | 42.8 | 1318.3 ms | 0 |
Validation timeline
| Validated | Summary | Score | Protocol | Auth mode | Tools | High-risk tools | Changes |
|---|---|---|---|---|---|---|---|
| Aug 04, 2026 08:50:36 PM UTC | Healthy | 73.8 | 2025-06-18 | oauth_supported | 12 | 1 | auth_mode_changed write_surface_expanded tool_snapshot_changed |
| Jul 31, 2026 06:37:41 AM UTC | Healthy | 42.8 | unknown | unknown | 0 | 0 | none |
Recent validation runs
| Started | Status | Summary | Latency | Checks |
|---|---|---|---|---|
| Aug 04, 2026 08:50:34 PM UTC | Completed | Healthy | 1599.1 ms | action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe |
| Jul 31, 2026 06:37:40 AM UTC | Completed | Healthy | 1318.3 ms | |
Public server reputation
Validation success 7d
1.0
Validation success 30d
1.0
Mean time to recover
n/a
Breaking diffs 30d
1
Registry drift frequency 30d
0
Snapshot changes 30d
1
Incident & change feed
| Timestamp | Event | Details |
|---|---|---|
| Aug 04, 2026 08:50:36 PM UTC | Latest validation: healthy | Score 73.8 with status healthy. |
| Aug 04, 2026 08:50:36 PM UTC | Score changed | Score delta +31.0 versus the previous run. |
| Aug 04, 2026 08:50:36 PM UTC | Tool snapshot changed | Added 12, removed 0, and changed 0 tool contracts. |
| Aug 04, 2026 08:50:36 PM UTC | Auth mode changed | Auth mode moved from unknown to oauth_supported. |
Capabilities
- OAuth:
- DCR/CIMD:
- Prompts:
- Homepage: https://forkmate.ai
- Docs: none
- Support: none
- Icon: none
- Remote endpoint: https://mcp.forkmate.ai/
- Server card: none
Use-case taxonomy
development database search communication
Benchmark tasks
| Benchmark task | Status | Evidence |
|---|---|---|
| Discover tools | Passes |
|
| Read-only fetch flow | Degraded |
|
| OAuth-required connect | Passes |
|
| Safe write flow with confirmation | Degraded |
|
Utility coverage
Probe status
OK
Completions
not detected
Completion probe target: none
Pagination
not detected
No nextCursor evidence.
Tasks
Auth Required
Advertised: no
Transport compliance drilldown
Probe status
Error
Transport
streamable-http
Session header
no
Protocol header
no
Bad protocol response
200
DELETE teardown
n/a
Expired session retry
n/a
Last-Event-ID visible
no
Issues: missing_session_id, missing_protocol_header, bad_protocol_not_rejected
Request association
Status
Missing
Advertised capabilities
none
Observed idle methods
none
Violating methods
none
Probe HTTP status
n/a
Issues
none
Connector replay
Status
OK
Backward compatible
Would break after refresh
Added tools
none
Removed tools
none
Additive output changes
none
Required-argument replay breaks
| Tool | Added required args | Removed required args |
|---|---|---|
| No required-argument replay breaks detected. | ||
Output-schema replay breaks
| Tool | Removed properties | Added properties |
|---|---|---|
| No output-schema replay breaks detected. | ||
Tool snapshot diff & changelog
Snapshot changed
yes
Added tools
add_pantry_item delete_meal get_day get_pantry get_preferences get_range log_meal lookup_barcode remove_pantry_item search_foods update_meal whoami
Removed tools
none
Required-argument changes
| Tool | Added required args | Removed required args |
|---|---|---|
| No required-argument changes detected. | ||
Output-schema drift
| Tool | Previous properties | Latest properties |
|---|---|---|
| No output-schema drift detected. | ||
Validation diff
Score delta
31.01
Summary changed
no
Tool delta
12
Prompt delta
0
Auth mode changed
yes
Write surface expanded
yes
Protocol regressed
no
Registry drift changed
no
Regressed checks: server_card, transport_compliance_probe
Improved checks: connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompts_list, provenance_divergence_probe, resources_list, tool_snapshot_probe, tools_list, utility_coverage_probe
| Component | Previous | Latest | Delta |
|---|---|---|---|
backward_compatibility_score | 2.0 | 4.0 | 2.0 |
advanced_capability_coverage_score | 3.0 | 1.25 | -1.75 |
trust_confidence_score | 1.75 | 2.94 | 1.19 |
connector_replay_score | 3.0 | 4.0 | 1.0 |
data_exfiltration_resilience_score | 2.0 | 3.0 | 1.0 |
least_privilege_scope_score | 2.0 | 3.0 | 1.0 |
result_shape_stability_score | 2.0 | 3.0 | 1.0 |
tool_snapshot_churn_score | 3.0 | 4.0 | 1.0 |
Registry & provenance divergence
Probe status
OK
Direct official match
yes
Drift fields
none
| Field | Registry | Live server card |
|---|---|---|
| Title | n/a | n/a |
| Version | n/a | n/a |
| Homepage | n/a | n/a |
Active alerts
- Tool snapshot changed (high)
Tools were added, removed, or materially changed between the latest two validations. - Auth mode changed (high)
Auth mode changed from unknown to oauth_supported. - Write-action surface expanded (high)
The number of high-risk write, delete, exec, or bulk-access tools increased on the latest run.
Aliases & registry graph
| Identifier | Source | Canonical | Score |
|---|---|---|---|
ai.forkmate/forkmate |
official_registry | yes | 73.8 |
Alias consolidation
Canonical identifier
ai.forkmate/forkmate
Duplicate aliases
0
Registry sources
official_registry
Remote URLs
Homepages
Source disagreements
| Field | What differs | Observed values |
|---|---|---|
| No source disagreements detected. | ||
Fix it
Why this score?
Access & Protocol
35/44
Connectivity, auth, and transport expectations for common clients.
Interface Quality
34.25/56
How well the tool/resource interface communicates and behaves under automation.
Security Posture
26/36
How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.
Reliability & Trust
21.94/24
Operational stability, consistency, and trustworthiness over time.
Discovery & Governance
21.5/28
How well the server is documented, listed, and governed in public registries.
Adoption & Market
6/8
Adoption clues and public evidence that the server is intended for external use.
Algorithmic score breakdown
Auth Operability
4/4
Measures whether auth discovery and protected access behave predictably for clients.
Error Contract Quality
0/4
Grades machine-readable error structure, status alignment, and remediation hints.
Rate-Limit Semantics
2/4
Checks whether quota/throttle responses are deterministic and automation-friendly.
Schema Completeness
3/4
Completeness of tool descriptions, parameter docs, examples, and schema shape.
Backward Compatibility
4/4
Stability score across tool schema/name drift relative to prior validations.
SLO Health
4/4
Availability, latency, and burst-failure profile across recent validation history.
Security Hygiene
4/4
HTTPS posture, endpoint hygiene, and response-surface hardening checks.
Task Success
4/4
Can an agent reliably initialize, enumerate tools, and execute core MCP flows?
Trust Confidence
2.9/4
Confidence-adjusted reliability score that penalizes low evidence volume.
Abuse/Noise Resilience
4/4
How well the server preserves core behavior in the presence of noisy traffic patterns.
Prompt Contract
2/4
Quality of prompt metadata, argument shape, and prompt discoverability for clients.
Resource Contract
2/4
How completely resources and resource templates describe URIs, types, and usage shape.
Discovery Metadata
4/4
Homepage, docs, icon, repository, support, and license coverage for directory consumers.
Registry Consistency
2/4
Agreement between stored registry metadata, live server-card data, and current validation output.
Installability
4/4
How cleanly a real client can connect, initialize, enumerate tools, and proceed through auth.
Session Semantics
4/4
Determinism and state behavior across repeated MCP calls, including sticky-session surprises.
Tool Surface Design
3/4
Naming clarity, schema ergonomics, and parameter complexity across the tool surface.
Result Shape Stability
3/4
Stability of declared output schemas across validations, with penalties for drift or missing shapes.
OAuth Interop
4/4
Depth and client compatibility of OAuth/OIDC metadata beyond the minimal protected-resource check.
Recovery Semantics
0/4
Whether failures include actionable machine-readable next steps such as retry or upgrade guidance.
Maintenance Signal
3/4
Versioning, update recency, and historical validation cadence that indicate active stewardship.
Adoption Signal
3/4
Directory presence and distribution clues that suggest the server is intended for external use.
Freshness Confidence
3/4
Confidence that recent validations are current enough and dense enough to trust operationally.
Transport Fidelity
4/4
Whether declared transport metadata matches the observed endpoint behavior and response formats.
Spec Recency
3/4
How close the server’s claimed MCP protocol version is to the latest known public revision.
Session Resume
3/4
Whether Streamable HTTP session identifiers and resumed requests behave cleanly for real clients.
Step-Up Auth
3/4
Whether OAuth metadata and WWW-Authenticate challenges support granular, incremental consent instead of broad upfront scopes.
Transport Compliance
0/4
Checks session headers, protocol-version enforcement, session teardown, and expired-session behavior.
Utility Coverage
2/4
Signals support for completions, pagination, and task-oriented utility surfaces that larger clients increasingly expect.
Advanced Capability Coverage
1.2/4
Coverage of newer MCP surfaces like roots, sampling, elicitation, structured output, and related metadata.
Connector Publishability
3/4
How ready the server looks for client catalogs and managed connector programs.
Tool Snapshot Churn
4/4
Stability of the tool surface across recent validations, including add/remove and output-shape drift.
Connector Replay
4/4
Whether a previously published frozen connector snapshot would remain backward compatible after the latest tool refresh.
Request Association
3/4
Whether roots, sampling, and elicitation appear tied to active client requests instead of arriving unsolicited on idle sessions.
Interactive Flow Safety
3/4
Whether prompts and docs steer users toward safe auth flows instead of pasting secrets directly.
Action Safety
2/4
Risk-weighted view of destructive, exec, egress, and confirmation semantics across the tool surface.
Official Registry Presence
4/4
Whether the server appears directly or indirectly in the official MCP registry.
Provenance Divergence
4/4
How closely official registry metadata, the live server card, and public repo/package signals agree with each other.
Safety Transparency
2/4
Clarity of docs, auth disclosure, support links, and other trust signals visible to integrators.
Tool Capability Clarity
4/4
How clearly the tool surface communicates whether each action reads, writes, deletes, executes, or exports data.
Destructive Operation Safety
2/4
Penalizes delete/revoke/destroy style tools unless auth and safeguards reduce blast radius.
Egress / SSRF Resilience
3/4
Assesses arbitrary URL fetch, crawl, webhook, and remote-request exposure on the tool surface.
Execution / Sandbox Safety
3/4
Evaluates shell, code, script, and command-execution exposure and whether that surface appears contained.
Data Exfiltration Resilience
3/4
Assesses export, dump, backup, and bulk-read behavior against the surrounding auth and safeguard signals.
Least Privilege Scope
3/4
Rewards scoped auth metadata and penalizes broad or missing scopes around privileged tools.
Secret Handling Hygiene
3/4
Assesses secret-bearing tools, token leakage risk, and whether the public surface avoids obvious secret exposure.
Supply Chain Signal
2.5/4
Public metadata signal for repository, changelog, license, versioning, and recency that supports supply-chain trust.
Input Sanitization Safety
3/4
Penalizes risky freeform string inputs when schemas do not constrain URLs, code, paths, queries, or templates.
Tool Namespace Clarity
4/4
Measures naming uniqueness and ambiguity across the tool namespace to reduce collision and confusion risk.
Actionable remediation
| Severity | Remediation | Why it matters | Recommended action |
|---|---|---|---|
| High | Add confirmation and dry-run semantics for risky actions | High-risk write, delete, exec, or egress tools should communicate safeguards clearly. | Add an explicit confirm/dry-run parameter or two-step confirmation flow to write, delete, exec, and egress-capable tools before they can make destructive changes.Playbook
|
| High | Align session and protocol behavior with Streamable HTTP expectations | Clients increasingly rely on MCP-Protocol-Version, session teardown, and expired-session semantics. | Align MCP-Protocol-Version, MCP-Session-Id, DELETE teardown, and expired-session handling with the transport spec.Playbook
|
| High | Associate roots, sampling, and elicitation with active client requests | Modern MCP guidance expects roots, sampling, and elicitation traffic to be tied to an active client request instead of arriving unsolicited on idle sessions. | Only send roots/list, sampling/createMessage, or elicitation/create requests while handling an active client-initiated request, never on idle sessions.Playbook
|
| High | Publish a complete server card | Missing or incomplete server-card metadata weakens discovery, documentation, and trust signals. | Serve /.well-known/mcp/server-card.json and include tools, prompts/resources, homepage, and support links.Playbook
|
| High | Respond to auth mode changed | Auth mode changed from unknown to oauth_supported. | Document the new auth posture and confirm protected-resource and challenge metadata still match reality. |
| High | Respond to tool snapshot changed | Tools were added, removed, or materially changed between the latest two validations. | Publish a first-class changelog for tool additions, removals, and breaking schema changes.Playbook
|
| High | Respond to write-action surface expanded | The number of high-risk write, delete, exec, or bulk-access tools increased on the latest run. | Review the newly exposed write and destructive actions before publishing them broadly.Playbook
|
| Medium | Adopt a current MCP protocol revision | Older protocol revisions reduce compatibility with newer clients and registry programs. | Advertise a current MCP protocol revision (2025-06-18 or later) in both the initialize response and the MCP-Protocol-Version header.Playbook
|
| Medium | Close connector-publishing gaps | Connector catalogs care about protocol recency, session behavior, auth clarity, and tool-surface stability. | |
| Medium | Document minimal scopes and return cleaner auth challenges | Modern clients expect granular scopes and step-up auth signals such as WWW-Authenticate scope hints. | Return granular scopes and WWW-Authenticate challenge hints instead of forcing overly broad auth upfront.Playbook
|
| Medium | Support resumable HTTP sessions cleanly | Modern MCP clients increasingly expect resumable session behavior on streamable HTTP transports. | Persist session state keyed by Mcp-Session-Id and honor Last-Event-ID on GET reconnects so clients can resume a dropped Streamable HTTP session.Playbook
|
| Low | Publish newer MCP capability signals | Roots, sampling, elicitation, structured outputs, and related metadata improve client understanding and ranking. | Advertise only the advanced capabilities (roots, sampling, elicitation) you have actually implemented end to end in the initialize capabilities object.Playbook
|
Point loss breakdown
| Component | Current | Points missing |
|---|---|---|
| Transport Compliance | 0/4 | -4.0 |
| Recovery Semantics | 0/4 | -4.0 |
| Error Contract | 0/4 | -4.0 |
| Advanced Capability Coverage | 1.2/4 | -2.8 |
| Utility Coverage | 2/4 | -2.0 |
| Safety Transparency | 2/4 | -2.0 |
| Resource Contract | 2/4 | -2.0 |
| Registry Consistency | 2/4 | -2.0 |
| Rate Limit Semantics | 2/4 | -2.0 |
| Prompt Contract | 2/4 | -2.0 |
| Destructive Operation Safety | 2/4 | -2.0 |
| Action Safety | 2/4 | -2.0 |
Compatibility profiles
OpenAI Connectors
88.9
compatible
Transport compliance should be in good shape.
Connector URL: https://mcp.forkmate.ai/ # Complete OAuth in the client when prompted. # Server: ai.forkmate/forkmate
Claude Desktop
83.3
compatible
Transport behavior should match Claude-compatible HTTP expectations.
{
"mcpServers": {
"forkmate": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.forkmate.ai/"]
}
}
}
Smithery
80.0
compatible
Machine-readable failure semantics should be present.
smithery mcp add "https://mcp.forkmate.ai/"
Generic Streamable HTTP
100.0
compatible
No major blockers detected.
curl -sS https://mcp.forkmate.ai/ -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'
Governance
MCP TrustOps
TrustOps turns this report into operational controls: freshness SLAs, authenticated validation, semantic benchmarks, policy exports, alert subscriptions, badges, cost/compliance metadata, and runtime routing. Fresh trusted index decisions stay separate from long-tail inventory so stale scores do not masquerade as current evidence.
Evidence age tier
Verified in last 24h
Policy SLA (contractual, distinct from the public 24h freshness window): 168.0h • confidence-weighted score (display score discounted for evidence age and confidence -- an internal TrustOps input, not the public score): 57.2 • evidence too old to display:
Policy exports
Formats: json, rego, yaml, github_action, gateway_config, client_report
Runtime routing
/v1/decideReturns allowed tools, blocked tools, approval requirement, and reason.
Hosted runtime
Deploy trusted servers from GitHub with secrets, egress controls, releases, rollback, and audit events.
Authenticated validation
Premium publisher feature: paid authenticated runs verify scopes, write-action safeguards, and authorized tool execution.
Active trust badges
Freshly Validated OAuth Verified OpenAI App Compatible Claude Remote MCP Compatible No Critical Risk
Semantic benchmarks
available
Templates cover GitHub, database, healthcare, web search, and CRM least-privilege jobs.
Supply chain
metadata signal
Deep scan checks are marked separately from public metadata signals.
Compliance metadata
Terms, privacy, SOC 2, HIPAA, GDPR, retention, deletion, and audit-log fields are tracked as enterprise metadata.
Alert subscription types
Status changes Score drops or recovers Freshness SLA breach Validation schema drift OAuth or auth behavior changes Tool surface changes New or changed write tool Supply-chain signal changes Legal or compliance metadata changes
MCP Runtime hosting
Verify Hosted MCP turns a trusted server report into a managed remote MCP endpoint with GitHub deployment provenance, sandbox policy, encrypted secrets, release history, rollback, and audit/usage events.
Activation readiness
Trusted hosted runtimes require fresh validation, a passing server state, a remote endpoint, and a minimum score.
Minimum tier
TrustOps
Publisher claim plus paid TrustOps tier are required before secrets or releases can be created.
Hosted endpoint
/hosted/{namespace}/{name}/mcpThe endpoint enforces egress allowlists and records audit/usage events.
Blockers
none
| Deployment | Status | Endpoint | Release |
|---|---|---|---|
| No hosted runtime deployments yet. | |||
Authenticated validation sessions
Public validation is free. Authenticated validation is paid and proves scoped behavior, write-action safeguards, and authenticated tool execution.
Latest profile
remote_mcp
Authenticated session used
Public score isolation
Preview endpoint
/v1/verifyCI preview endpoint
/v1/ci/previewInstall snippets
Openai Connectors
Connector URL: https://mcp.forkmate.ai/ # Complete OAuth in the client when prompted. # Server: ai.forkmate/forkmate
Claude Desktop
{
"mcpServers": {
"forkmate": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.forkmate.ai/"]
}
}
}
Smithery
smithery mcp add "https://mcp.forkmate.ai/"
Generic Http
curl -sS https://mcp.forkmate.ai/ -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'
Agent access & tool surface
Live server tools
whoami get_day get_range get_preferences log_meal update_meal delete_meal get_pantry
Observed from the latest live validation against https://mcp.forkmate.ai/. This is the target server surface, not Verify's own inspection tools.
Live capability counts
12 tools • 0 prompts • 0 resources
Counts come from the latest
tools/list, prompts/list, and resources/list checks.Inspect with Verify
search fetch search_servers recommend_servers get_server_report compare_servers
Use Verify itself to search, recommend, compare, and fetch the full report for
ai.forkmate/forkmate.Direct machine links