ai.foura/mcp
ai.foura/mcp
Reliable web access for AI agents: smart HTTP, rotating proxies, and full-browser rendering.
DECISION SUMMARY
Allow With Approval
Score
74.0
Top 8.0% of 287 scored public servers
Confidence
High
Based on evidence completeness, recency, and validation density.
Evidence age
20.1h old
Freshness: fresh. Snapshot
trustsnap_5e3f21ec74da2a62.Top risk drivers
- Utility Coverage
- Recovery Semantics
- Advanced Capability Coverage
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
write/admin actions need confirmation safeguards
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
74.0
Transport
streamable-http
Tools
4
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
4
High-risk tools
0
Destructive tools
0
Exec tools
0
Egress tools
0
Secret tools
0
Bulk-access tools
0
Risk distribution
low:4
Tool capability & risk inventory
| Tool | Capabilities | Risk | Findings | Notes |
|---|---|---|---|---|
foura_single |
read | Low | none | No explicit safeguard hints detected. |
foura_proxy |
read | Low | none | Safeguards hinted in metadata. |
foura_browser |
read | Low | none | No explicit safeguard hints detected. |
foura_auto |
read | Low | none | Safeguards hinted in metadata. |
Write-action governance
Governance status
Error
Safe to publish
Auth boundary
public_or_unclear
Blast radius
Low
High-risk tools
0
Confirmation signals
none
Safeguard count
2
Status detail: No high-risk write actions are exposed without a clear auth boundary; 2 safeguard(s) and 0 confirmation signal(s) detected.
| Tool | Risk | Flags | Safeguards |
|---|---|---|---|
| No high-risk tools were detected on the latest run. | |||
Action-controls diff
Snapshot changed
yes
Disabled-by-default candidates
none
Manual review candidates
none
New actions
| Action | Risk | Flags |
|---|---|---|
foura_auto | Low | none |
foura_browser | Low | none |
foura_proxy | Low | none |
foura_single | 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
Partially client-compatible
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.
Confidence: high (77.5)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
initialize• OKtools_list• OKtransport_compliance_probe• Warningstep_up_auth_probe• Missingconnector_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
No major blockers detected.
Confidence: high (77.5)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
initialize• OKtools_list• OKtransport_compliance_probe• Warning
Write-action publishing
Publishing blocked
Blocked until safeguards and confirmation semantics are verified for write, exec, or destructive tools.
Confidence: high (77.5)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history
Disagreements: none
action_safety_probe• Error
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
Partially client-compatible
Remediation checklist
OpenAI connectors expect OAuth for remote server auth.Dynamic client registration materially improves connector setup.OAuth is not configured, so this client cannot authenticate without additional setup.Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.Transport compliance issues should be resolved before wider client rollout.
Claude remote MCP
Client-compatible
Remediation checklist
OAuth is not configured, so this client cannot authenticate without additional setup.Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.Transport compliance issues should be resolved before wider client rollout.
Write-safe publishing
Blocked
Remediation checklist
Add a clearer auth boundary around risky write actions.Add confirmation or dry-run semantics for risky actions.
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 |
Partially 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 blocked | 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
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup. Compatibility is not a production approval; company knowledge and Messages API gates remain separate.
- Search Fetch Only: Yes
- Write Actions Present: No
- Oauth Configured: No
- Admin Refresh Required: No
- Safe For Company Knowledge: Yes
- Safe For Messages Api Remote Mcp: No
Claude remote MCP compatibility
Connector-compatible
Transport, discovery, and remote-MCP assumptions are satisfied. Compatibility is not a production approval; company knowledge and Messages API gates remain separate.
- Search Fetch Only: Yes
- Write Actions Present: No
- Oauth Configured: No
- Admin Refresh Required: No
- Safe For Company Knowledge: Yes
- Safe For Messages Api Remote Mcp: No
Compatibility fixtures
ChatGPT custom connector fixture
Degraded
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.
- remote_http_endpoint: Passes
- oauth_discovery: Degraded
- frozen_tool_snapshot_refresh: Passes
- request_association: Passes
Anthropic remote MCP fixture
Passes
Remote MCP transport and discovery assumptions are satisfied.
- remote_transport: Passes
- tool_discovery: Passes
- auth_connect: Passes
- safe_write_review: Degraded
Recommended for
Claude Desktop
Claude Desktop is marked compatible with score 100.
Smithery
Smithery is marked compatible with score 100.
Generic Streamable HTTP
Generic Streamable HTTP is marked compatible with score 100.
Evidence
Current trust snapshot
Snapshot ID
trustsnap_5e3f21ec74da2a62Use this ID to compare server page, report, policy, MCP, homepage, ranking, and shortlist surfaces.
Snapshot generated
Aug 05, 2026 04:56:22 PM UTC
All page, report, policy, and MCP surfaces use this same server-detail snapshot shape.
Last validated
Aug 04, 2026 08:50:49 PM UTC
Age: 20.09h • evidence age tier: Verified in last 24h • display score: 73.95
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 08:50:46 PM UTC
Latency
3672.8 ms
Failures
oauth_authorization_serverno authorization serveroauth_protected_resourceClient error '404 Not Found' for url 'https://mcp.foura.ai/.well-known/oauth-protected-resource' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404openid_configurationno authorization serverprompt_getJSON-RPC error -32602: MCP error -32602: Invalid arguments for prompt scrape_product_page: [ { "expected": "string", "code": "invalid_type", "path": [ "url" ], "message": "Invalid input: expected string, received undefined" } ]server_cardClient error '404 Not Found' for url 'https://mcp.foura.ai/.well-known/mcp/server-card.json' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
Checks
| Check | Status | Latency | Evidence |
|---|---|---|---|
action_safety_probe |
Error | n/a | 3 high-risk, 1 destructive, 2 exec-capable tool(s); no clear auth boundary; safeguards=2; confirmation=none. |
advanced_capabilities_probe |
Warning | n/a | Only 3 capability signal(s): prompts, resources, structured outputs. |
connector_publishability_probe |
Warning | n/a | Publishability blockers: action safety, server card. |
connector_replay_probe |
OK | n/a | Backward compatible with no breaking tool-surface changes. |
determinism_probe |
OK | 289.1 ms | Check completed |
initialize |
OK | 290.6 ms | Protocol 2025-03-26 |
interactive_flow_probe |
OK | n/a | Check completed |
oauth_authorization_server |
Missing | n/a | no authorization server |
oauth_protected_resource |
Error | 440.3 ms | Client error '404 Not Found' for url 'https://mcp.foura.ai/.well-known/oauth-protected-resource' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404 |
official_registry_probe |
OK | n/a | Check completed |
openid_configuration |
Missing | n/a | no authorization server |
probe_noise_resilience |
OK | 285.2 ms | Fetched https://mcp.foura.ai/robots.txt |
prompt_get |
Error | 288.1 ms | JSON-RPC error -32602: MCP error -32602: Invalid arguments for prompt scrape_product_page: [ { "expected": "string", "code": "invalid_type", "path": [ "url" ], "message": "Invalid input: expected string, received undefined" } ] |
prompts_list |
OK | 289.2 ms | 6 prompt(s) exposed |
protocol_version_probe |
Warning | n/a | Claims 2025-03-26; 2 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 | 291.1 ms | 0 resource item(s) exposed |
server_card |
Error | 417.4 ms | Client error '404 Not Found' for url 'https://mcp.foura.ai/.well-known/mcp/server-card.json' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404 |
session_resume_probe |
Warning | n/a | no session id |
step_up_auth_probe |
Missing | n/a | No OAuth or incremental-scope signals detected. |
tool_snapshot_probe |
OK | n/a | Check completed |
tools_list |
OK | 389.7 ms | 4 tool(s) exposed |
transport_compliance_probe |
Warning | 291.5 ms | Issues: missing session id, missing protocol header (bad protocol=400). |
utility_coverage_probe |
Missing | 97.7 ms | No completions evidence; no pagination evidence; tasks missing. |
Raw evidence view
Show raw JSON evidence
{
"checks": {
"action_safety_probe": {
"details": {
"auth_present": false,
"confirmation_signals": [],
"safeguard_count": 2,
"summary": {
"bulk_access_tools": 0,
"capability_distribution": {
"admin": 4,
"delete": 1,
"exec": 2,
"network": 4,
"read": 4,
"secrets": 2,
"write": 4
},
"destructive_tools": 1,
"egress_tools": 4,
"exec_tools": 2,
"high_risk_tools": 3,
"risk_distribution": {
"critical": 2,
"high": 1,
"low": 0,
"medium": 1
},
"secret_tools": 2,
"tool_count": 4
}
},
"latency_ms": null,
"status": "error"
},
"advanced_capabilities_probe": {
"details": {
"capabilities": {
"completions": false,
"elicitation": false,
"prompts": true,
"resource_links": false,
"resources": true,
"roots": false,
"sampling": false,
"structured_outputs": true
},
"enabled": [
"prompts",
"resources",
"structured_outputs"
],
"enabled_count": 3,
"initialize_capability_keys": [
"prompts",
"resources",
"tools"
]
},
"latency_ms": null,
"status": "warning"
},
"connector_publishability_probe": {
"details": {
"blockers": [
"action_safety",
"server_card"
],
"criteria": {
"action_safety": false,
"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": true
},
"high_risk_tools": 3,
"tool_count": 4,
"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": "4065461dea3c8b72e68b3d23c61b50201b3ec53b5b51ee0b821b771d35abfed0",
"errors": [],
"matches": 2,
"stable_ratio": 1.0,
"successful": 2
},
"latency_ms": 289.06,
"status": "ok"
},
"initialize": {
"details": {
"headers": {
"content-type": "text/event-stream",
"strict-transport-security": "max-age=31536000; includeSubDomains; preload"
},
"http_status": 200,
"payload": {
"id": 1,
"jsonrpc": "2.0",
"result": {
"capabilities": {
"prompts": {
"listChanged": true
},
"resources": {
"listChanged": true
},
"tools": {
"listChanged": true
}
},
"protocolVersion": "2025-03-26",
"serverInfo": {
"description": "Reliable web access for AI agents: smart HTTP, rotating proxies, and full-browser rendering.",
"icons": [
{
"mimeType": "image/png",
"sizes": [
"512x512"
],
"src": "https://foura.ai/logo/avatars/4a-transparent-indigo-512.png"
}
],
"name": "foura-mcp",
"title": "FourA",
"version": "0.5.0",
"websiteUrl": "https://foura.ai/mcp"
}
}
},
"url": "https://mcp.foura.ai/mcp"
},
"latency_ms": 290.59,
"status": "ok"
},
"interactive_flow_probe": {
"details": {
"oauth_supported": false,
"prompt_available": false,
"risk_hits": [],
"safe_hits": [
"browser"
]
},
"latency_ms": null,
"status": "ok"
},
"oauth_authorization_server": {
"details": {
"reason": "no_authorization_server"
},
"latency_ms": null,
"status": "missing"
},
"oauth_protected_resource": {
"details": {
"error": "Client error '404 Not Found' for url 'https://mcp.foura.ai/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
"url": "https://mcp.foura.ai/.well-known/oauth-protected-resource"
},
"latency_ms": 440.3,
"status": "error"
},
"official_registry_probe": {
"details": {
"direct_match": true,
"official_peer_count": 1,
"registry_identifier": "ai.foura/mcp",
"registry_source": "official_registry"
},
"latency_ms": null,
"status": "ok"
},
"openid_configuration": {
"details": {
"reason": "no_authorization_server"
},
"latency_ms": null,
"status": "missing"
},
"probe_noise_resilience": {
"details": {
"headers": {
"content-type": "text/plain",
"strict-transport-security": "max-age=31536000; includeSubDomains; preload"
},
"http_status": 404,
"url": "https://mcp.foura.ai/robots.txt"
},
"latency_ms": 285.19,
"status": "ok"
},
"prompt_get": {
"details": {
"headers": {
"content-type": "text/event-stream",
"strict-transport-security": "max-age=31536000; includeSubDomains; preload"
},
"http_status": 200,
"payload": {
"error": {
"code": -32602,
"message": "MCP error -32602: Invalid arguments for prompt scrape_product_page: [\n {\n \"expected\": \"string\",\n \"code\": \"invalid_type\",\n \"path\": [\n \"url\"\n ],\n \"message\": \"Invalid input: expected string, received undefined\"\n }\n]"
},
"id": 4,
"jsonrpc": "2.0"
},
"prompt_arguments": [
{
"description": "Product page URL (any e-commerce site)",
"name": "url",
"required": true
}
],
"prompt_name": "scrape_product_page",
"url": "https://mcp.foura.ai/mcp"
},
"latency_ms": 288.1,
"status": "error"
},
"prompts_list": {
"details": {
"headers": {
"content-type": "text/event-stream",
"strict-transport-security": "max-age=31536000; includeSubDomains; preload"
},
"http_status": 200,
"payload": {
"id": 3,
"jsonrpc": "2.0",
"result": {
"prompts": [
{
"arguments": [
{
"description": "Product page URL (any e-commerce site)",
"name": "url",
"required": true
}
],
"description": "Fetch an e-commerce product URL and extract structured product info as JSON (title, price, image, availability).",
"name": "scrape_product_page",
"title": "Scrape a product page"
},
{
"arguments": [
{
"description": "Article URL",
"name": "url",
"required": true
}
],
"description": "Fetch a news/blog article URL and extract the main content (headline, author, body, date) stripped of nav/ads/footer.",
"name": "extract_article",
"title": "Extract an article"
},
{
"arguments": [
{
"description": "Pricing or product page URL",
"name": "url",
"required": true
},
{
"description": "Optional target price to compare against (e.g. \"19.99\")",
"name": "target_price",
"required": false
}
],
"description": "Fetch a pricing page and extract the current price; compare to a target if provided.",
"name": "monitor_pricing",
"title": "Monitor a price"
},
{
"arguments": [
{
"description": "HTTP endpoint URL to probe",
"name": "url",
"required": true
},
{
"description": "Optional substring that must appear in the response body for the endpoint to count as healthy",
"name": "expected_text",
"required": false
}
],
"description": "GET a URL through foura_single with strict validation and report whether it's reachable and responding correctly.",
"name": "check_endpoint_health",
"title": "Check API endpoint health"
},
{
"arguments": [
{
"description": "Comma-separated list of URLs to fetch",
"name": "urls",
"required": true
}
],
"description": "Fetch multiple URLs concurrently and return each outcome. Retry blocked URLs through foura_proxy.",
"name": "bulk_fetch_urls",
"title": "Fetch a list of URLs in parallel"
},
{
"arguments": [
{
"description": "URL to fetch",
"name": "url",
"required": true
},
{
"description": "Optional substring the real page must contain - lets auto tell a real page from a challenge page on protected targets.",
"name": "must_contain",
"required": false
},
{
"description": "Optional plain-English description of what to pull out of the page (e.g. \"title, price, image\").",
"name": "extract",
"required": false
}
],
"description": "Fetch any URL with foura_auto - one call that picks the method (direct / proxy / browser), gets past common bot protection, and returns the content. Use when you just want the page and don't want to choose a tool.",
"name": "smart_fetch",
"title": "Fetch a URL the smart way (auto)"
}
]
}
},
"url": "https://mcp.foura.ai/mcp"
},
"latency_ms": 289.19,
"status": "ok"
},
"protocol_version_probe": {
"details": {
"claimed_version": "2025-03-26",
"lag_days": 244,
"latest_known_version": "2025-11-25",
"releases_behind": 2,
"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": "text/event-stream",
"strict-transport-security": "max-age=31536000; includeSubDomains; preload"
},
"http_status": 200,
"payload": {
"id": 5,
"jsonrpc": "2.0",
"result": {
"resources": []
}
},
"url": "https://mcp.foura.ai/mcp"
},
"latency_ms": 291.11,
"status": "ok"
},
"server_card": {
"details": {
"error": "Client error '404 Not Found' for url 'https://mcp.foura.ai/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
"url": "https://mcp.foura.ai/.well-known/mcp/server-card.json"
},
"latency_ms": 417.37,
"status": "error"
},
"session_resume_probe": {
"details": {
"protocol_version": "2025-03-26",
"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": false,
"scope_specificity_ratio": 0.0,
"step_up_signals": [],
"supported_scopes": []
},
"latency_ms": null,
"status": "missing"
},
"tool_snapshot_probe": {
"details": {
"added": [],
"changed_outputs": [],
"current_tool_count": 4,
"previous_tool_count": 4,
"removed": [],
"similarity": 1.0
},
"latency_ms": null,
"status": "ok"
},
"tools_list": {
"details": {
"headers": {
"content-type": "text/event-stream",
"strict-transport-security": "max-age=31536000; includeSubDomains; preload"
},
"http_status": 200,
"payload": {
"id": 2,
"jsonrpc": "2.0",
"result": {
"tools": [
{
"annotations": {
"destructiveHint": false,
"openWorldHint": true,
"readOnlyHint": true
},
"description": "Send one HTTP request and return the response. Use it for static pages, JSON APIs, and server-rendered HTML. Set unblocker:true for targets that reject basic HTTP requests. Switch to foura_proxy if the response is blocked, and use foura_browser when the page needs JavaScript.",
"execution": {
"taskSupport": "forbidden"
},
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"accept_timeout_ms": {
"description": "Timeout in ms to receive the first response byte after the request is sent (0-120000). Omit for the default.",
"maximum": 120000,
"minimum": 0,
"type": "integer"
},
"connect_timeout_ms": {
"description": "Timeout in ms for establishing the TCP/TLS connection (0-120000). Omit to use the default.",
"maximum": 120000,
"minimum": 0,
"type": "integer"
},
"data": {
"anyOf": [
{
"type": "string"
},
{
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
}
],
"description": "Request body. Strings sent as-is; objects auto-serialized to JSON. Example: {\"query\": \"hello\"} for POST APIs."
},
"dns_cache_timeout_sec": {
"description": "How long (seconds) to cache the target's resolved DNS (0-240). Omit for the default.",
"maximum": 240,
"minimum": 0,
"type": "integer"
},
"followRedirects": {
"description": "Max number of redirects to follow (0-20). Omit to disable redirect following.",
"maximum": 20,
"minimum": 0,
"type": "integer"
},
"headers": {
"description": "Custom HTTP headers as [name, value] tuples. Example: [[\"Accept\", \"application/json\"], [\"Referer\", \"https://google.com/\"]]",
"items": {
"items": [
{
"type": "string"
},
{
"type": "string"
}
],
"type": "array"
},
"type": "array"
},
"method": {
"description": "HTTP method (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS, or any WebDAV verb like PROPFIND/MKCOL)",
"minLength": 1,
"type": "string"
},
"offload_large": {
"description": "If true, response bodies of 50 KB or more are returned as a resource_link instead of inlined. Default false. Read the returned offloaded_resource_uri with resources/read.",
"type": "boolean"
},
"proxy": {
"description": "Optional proxy. Two forms: (1) URL `http://host:port` or `socks5://host:port`; (2) base36 ID from foura_proxy (e.g. `4DZ3VE`) to reuse the same exit. For rotation, use foura_proxy.",
"type": "string"
},
"returnBuffer": {
"description": "Return raw bytes as a serialized Buffer JSON shape (`{type:\"Buffer\", data:[byte, ...]}`, bytes 0-255) instead of decoded string. Use for binary responses (images, protobuf). Reconstruct: `Buffer.from(data.data)` in Node, `new Uint8Array(data.data)` elsewhere.",
"type": "boolean"
},
"server_response_timeout_ms": {
"description": "Timeout in ms for the server to send the complete response (0-120000). Omit for the default.",
"maximum": 120000,
"minimum": 0,
"type": "integer"
},
"timeout_ms": {
"description": "Overall request timeout in ms (max 120000, default 15000)",
"maximum": 120000,
"minimum": 0,
"type": "integer"
},
"tryJsonData": {
"description": "If true, attempt JSON.parse on the response body. On success, `data` is the parsed value (typically object or array). On parse failure, `data` silently stays as the original string - no error, no warning. Set false (or omit) when you need to detect parse failures explicitly.",
"type": "boolean"
},
"unblocker": {
"description": "Add common browser headers such as User-Agent, Sec-Ch-Ua, and Accept-Encoding. Default false. Enable it for targets that reject basic HTTP requests.",
"type": "boolean"
},
"url": {
"description": "Public target URL. Private or reserved targets return `ssrf_blocked`. Use {ts} in the URL to insert the current Unix timestamp. Example: https://api.example.com/v1/users.",
"format": "uri",
"type": "string"
},
"validate": {
"description": "Post-fetch response validation. When the response fails these checks the tool returns an error envelope.",
"properties": {
"data": {
"description": "Body validation: pass when the body contains an expected substring (accept), fail when it contains a blocked one (fail).",
"properties": {
"accept": {
"description": "Substrings the response body must contain",
"items": {
"type": "string"
},
"type": "array"
},
"fail": {
"description": "Substrings the response body must not contain",
"items": {
"type": "string"
},
"type": "array"
}
},
"type": "object"
},
"headers": {
"description": "Header validation: pass when an accepted header matches, fail when a blocklisted header matches.",
"properties": {
"accept": {
"additionalProperties": {
"type": "string"
},
"description": "Case-insensitive header substring rules. The response passes when at least one name/value pair matches across the redirect chain.",
"propertyNames": {
"type": "string"
},
"type": "object"
},
"fail": {
"additionalProperties": {
"type": "string"
},
"description": "Case-insensitive header substring rules that reject the response when any name/value pair matches.",
"propertyNames": {
"type": "string"
},
"type": "object"
}
},
"type": "object"
},
"status": {
"description": "Status-code validation: which HTTP status codes count as success (accept) or failure (fail).",
"properties": {
"accept": {
"description": "HTTP status codes to treat as success",
"items": {
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"type": "array"
},
"fail": {
"description": "HTTP status codes to treat as failure",
"items": {
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"type": "array"
}
},
"type": "object"
}
},
"type": "object"
}
},
"required": [
"method",
"url"
],
"type": "object"
},
"name": "foura_single",
"outputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"code": {
"description": "Stable error code for retry classification. auth_failed means the FourA API key was rejected; verify that key, not target-site credentials. Other codes: ssrf_blocked, upstream_non_json, output_validation_failed, bad_request (400), forbidden (403), not_found (404), rate_limited (429), at_capacity (503), service_disabled (503), service_unavailable (503), upstream_error (>=500), upstream_client_error (other 4xx), upstream_unknown (defensive).",
"type": "string"
},
"current": {
"additionalProperties": false,
"description": "Caller's current usage at error time",
"properties": {
"concurrency": {
"type": "number"
},
"rpm": {
"type": "number"
}
},
"type": "object"
},
"data": {
"description": "Decoded response body. String by default; object when tryJsonData=true and the body parsed as JSON; serialized Buffer JSON shape (`{type:\"Buffer\", data:[byte, ...]}`, bytes 0-255) when returnBuffer=true - reconstruct with `Buffer.from(data.data)` in Node, `new Uint8Array(data.data)` elsewhere. Omitted when offloaded."
},
"error": {
"description": "Human-readable error message",
"type": "string"
},
"headers": {
"anyOf": [
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
}
]
},
"properties": {
"result": {
"additionalProperties": false,
"properties": {
"code": {
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"reason": {
"type": "string"
},
"version": {
"type": "string"
}
},
"type": "object"
}
},
"type": "object"
},
"type": "array"
},
{
"type": "string"
},
{
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
}
],
"description": "Response headers per redirect hop, as an array of objects. Each entry has `result.{version, code, reason}` plus arbitrary header-name keys whose values are strings (or arrays of strings for multi-value headers like Set-Cookie / Link). Last array entry is the final response."
},
"limits": {
"additionalProperties": false,
"description": "Per-service limits at error time",
"properties": {
"maxConcurrency": {
"type": "number"
},
"maxRpm": {
"type": "number"
}
},
"type": "object"
},
"offloaded_resource_uri": {
"description": "foura-mcp://payload/<uuid>. Pass this URI to resources/read to retrieve the offloaded body.",
"type": "string"
},
"retryAfter": {
"description": "Seconds to wait before retrying (429/503)",
"type": "number"
},
"service": {
"enum": [
"single",
"proxy",
"browser",
"api"
],
"type": "string"
},
"size_bytes": {
"description": "Total offloaded body size in bytes",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"status": {
"description": "HTTP status code from the target. `0` indicates the request failed before any HTTP response (DNS failure, connection refused, timeout) - check the `error` field for the underlying reason.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"total_time": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Wall-clock request duration in seconds. Number when present; string in some variants; null when the request never started."
}
},
"type": "object"
},
"title": "FourA - single HTTP request"
},
{
"annotations": {
"destructiveHint": false,
"openWorldHint": true,
"readOnlyHint": true
},
"description": "Route an HTTP request through rotating proxies with automatic retry. Use it when foura_single is blocked or the target requires a specific exit country. The response includes the proxy ID that succeeded; reuse it with foura_single or foura_browser, or exclude it with ignoreProxies. Use foura_browser when the page needs JavaScript. Set exitCountries for a strict country allowlist.",
"execution": {
"taskSupport": "forbidden"
},
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"exitCountries": {
"description": "Optional target-visible proxy countries as two-letter provider codes, for example [\"CZ\", \"GB\"]. Use codes supplied by the user or target requirements. When geography matters, do not guess codes or substitute unscoped rotation. Values are trimmed, uppercased, and deduplicated. Unknown exits are excluded and the request never falls back to another country.",
"items": {
"pattern": "^[A-Z]{2}$",
"type": "string"
},
"minItems": 1,
"type": "array"
},
"ignoreProxies": {
"description": "Encoded proxy IDs (base36 strings like \"4DZ3VE\") or proxy URLs to exclude from rotation.",
"items": {
"type": "string"
},
"type": "array"
},
"maxTries": {
"description": "Maximum rotation attempts before giving up (default 5, max 90). Difficult protected targets may need 25-30. Use exitCountries for country scope.",
"maximum": 90,
"minimum": 1,
"type": "integer"
},
"offload_large": {
"description": "If true, response bodies of 50 KB or more are returned as a resource_link instead of inlined. Default false. Read the returned offloaded_resource_uri with resources/read.",
"type": "boolean"
},
"request": {
"description": "The inner HTTP request to send through each proxy attempt. Validation rules here determine when a proxy is treated as failed and retried.",
"properties": {
"accept_timeout_ms": {
"description": "Timeout in ms to receive the first response byte after the request is sent (0-120000). Omit for the default.",
"maximum": 120000,
"minimum": 0,
"type": "integer"
},
"connect_timeout_ms": {
"description": "Timeout in ms for establishing the connection to the target through the proxy (0-120000). Omit for the default.",
"maximum": 120000,
"minimum": 0,
"type": "integer"
},
"data": {
"anyOf": [
{
"type": "string"
},
{
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
}
],
"description": "Request body."
},
"dns_cache_timeout_sec": {
"description": "How long (seconds) to cache the target's resolved DNS (0-240). Omit for the default.",
"maximum": 240,
"minimum": 0,
"type": "integer"
},
"followRedirects": {
"description": "Max number of redirects to follow (0-20). Omit to disable redirect following.",
"maximum": 20,
"minimum": 0,
"type": "integer"
},
"headers": {
"description": "Custom HTTP headers as [name, value] tuples. Example: [[\"Accept\", \"application/json\"]]",
"items": {
"items": [
{
"type": "string"
},
{
"type": "string"
}
],
"type": "array"
},
"type": "array"
},
"method": {
"description": "HTTP method (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS, or any WebDAV verb)",
"minLength": 1,
"type": "string"
},
"returnBuffer": {
"description": "Return raw bytes as a serialized Buffer JSON shape ({type:\"Buffer\", data:[byte, ...]}) instead of a decoded string. Use for binary responses (images, protobuf).",
"type": "boolean"
},
"server_response_timeout_ms": {
"description": "Timeout in ms for the server to send the complete response (0-120000). Omit for the default.",
"maximum": 120000,
"minimum": 0,
"type": "integer"
},
"timeout_ms": {
"description": "Per-attempt timeout in ms",
"maximum": 120000,
"minimum": 0,
"type": "integer"
},
"tryJsonData": {
"description": "If true, attempt JSON.parse on the response body; on success `data` is the parsed value, otherwise it stays the original string. Omit to keep the body as-is.",
"type": "boolean"
},
"unblocker": {
"description": "Add common browser headers such as User-Agent, Sec-Ch-Ua, and Accept-Encoding. Default false. Enable it for targets that reject basic HTTP requests.",
"type": "boolean"
},
"url": {
"description": "Public target URL. Private or reserved targets return `ssrf_blocked`. Use {ts} in the URL to insert the current Unix timestamp. Example: https://shop.example.com/pricing.",
"format": "uri",
"type": "string"
},
"validate": {
"description": "Per-attempt response validation. A proxy attempt that fails these checks is treated as failed and the next proxy is tried.",
"properties": {
"data": {
"description": "Body validation: pass when the body contains an expected substring (accept), fail when it contains a blocked one (fail).",
"properties": {
"accept": {
"description": "Substrings the response body must contain to pass.",
"items": {
"type": "string"
},
"type": "array"
},
"fail": {
"description": "Substrings that, if present in the body, mark the response as failed.",
"items": {
"type": "string"
},
"type": "array"
}
},
"type": "object"
},
"headers": {
"description": "Header validation: pass when an accepted header matches, fail when a blocklisted header matches.",
"properties": {
"accept": {
"additionalProperties": {
"type": "string"
},
"description": "Case-insensitive header substring rules. The response passes when at least one name/value pair matches across the redirect chain.",
"propertyNames": {
"type": "string"
},
"type": "object"
},
"fail": {
"additionalProperties": {
"type": "string"
},
"description": "Case-insensitive header substring rules that reject the response when any name/value pair matches.",
"propertyNames": {
"type": "string"
},
"type": "object"
}
},
"type": "object"
},
"status": {
"description": "Status-code validation: which HTTP status codes count as success (accept) or failure (fail).",
"properties": {
"accept": {
"description": "HTTP status codes to treat as success",
"items": {
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"type": "array"
},
"fail": {
"description": "HTTP status codes to treat as failure",
"items": {
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"type": "array"
}
},
"type": "object"
}
},
"type": "object"
}
},
"required": [
"method",
"url"
],
"type": "object"
},
"timeout_ms": {
"description": "Overall timeout across all rotation attempts in ms (default 45000, max 120000). Must be positive.",
"exclusiveMinimum": 0,
"maximum": 120000,
"type": "integer"
}
},
"required": [
"request"
],
"type": "object"
},
"name": "foura_proxy",
"outputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"code": {
"description": "Stable error code for retry classification. auth_failed means the FourA API key was rejected; verify that key, not target-site credentials. no_eligible_proxy means the strict exitCountries scope had no match. Keep that scope and retry later; do not propose or perform an unscoped fallback.",
"type": "string"
},
"current": {
"additionalProperties": false,
"properties": {
"concurrency": {
"type": "number"
},
"rpm": {
"type": "number"
}
},
"type": "object"
},
"data": {
"description": "Decoded response body. Omitted when offloaded."
},
"details": {
"additionalProperties": false,
"description": "Structured no_eligible_proxy context containing the normalized requested country scope. Preserve this scope and retry later. Do not propose or perform an unscoped fallback; change it only after the user explicitly changes the requirement.",
"properties": {
"exitCountries": {
"items": {
"pattern": "^[A-Z]{2}$",
"type": "string"
},
"minItems": 1,
"type": "array"
}
},
"required": [
"exitCountries"
],
"type": "object"
},
"error": {
"description": "Human-readable error message",
"type": "string"
},
"exitCountry": {
"description": "Latest available two-letter target-visible exit-country code used for selection. Present on successful requests that use exitCountries.",
"pattern": "^[A-Z]{2}$",
"type": "string"
},
"headers": {
"anyOf": [
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
}
]
},
"properties": {
"result": {
"additionalProperties": false,
"properties": {
"code": {
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"reason": {
"type": "string"
},
"version": {
"type": "string"
}
},
"type": "object"
}
},
"type": "object"
},
"type": "array"
},
{
"type": "string"
},
{
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
}
],
"description": "Response headers per redirect hop, as an array of objects. Each entry has `result.{version, code, reason}` plus arbitrary header-name keys whose values are strings (or arrays of strings for multi-value headers like Set-Cookie / Link)."
},
"limits": {
"additionalProperties": false,
"properties": {
"maxConcurrency": {
"type": "number"
},
"maxRpm": {
"type": "number"
}
},
"type": "object"
},
"offloaded_resource_uri": {
"description": "foura-mcp://payload/<uuid>. Pass this URI to resources/read to retrieve the offloaded body.",
"type": "string"
},
"proxy": {
"description": "Base36 ID of the exit that succeeded (e.g. `4DZ3VE`). Pass it to foura_single.proxy or foura_browser.proxy to reuse that exit, or to foura_proxy.ignoreProxies to skip it on future rotations.",
"type": "string"
},
"request": {
"description": "Echoed PrRequest from upstream PrResponseError"
},
"retryAfter": {
"type": "number"
},
"service": {
"enum": [
"single",
"proxy",
"browser",
"api"
],
"type": "string"
},
"size_bytes": {
"description": "Total offloaded body size in bytes",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"status": {
"description": "HTTP status code from the target (from the succeeding proxy attempt). `0` indicates every attempt failed before any HTTP response (DNS / connection refused / timeout) - check the `error` field for the underlying reason.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"total": {
"description": "Outer total time in seconds (proxy selection + retries + the successful inner attempt). Float.",
"type": "number"
},
"total_time": {
"anyOf": [
{
"type": "number"
},
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Per-attempt wall-clock duration of the succeeding inner request"
}
},
"type": "object"
},
"title": "FourA - HTTP request via rotating proxies"
},
{
"annotations": {
"destructiveHint": false,
"openWorldHint": true,
"readOnlyHint": true
},
"description": "Load a public URL in a full browser session. JavaScript runs, the DOM renders, and cookies come back with the response. Use it for single-page apps, lazy-loaded content, or supported browser challenges. For a protected page, call foura_proxy first and pass its returned proxy ID here to reuse that exit. Set unblocker:false when you want the page exactly as it loads.",
"execution": {
"taskSupport": "forbidden"
},
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"checkStatus": {
"description": "Expected HTTP status code. A different status returns an error envelope carrying the actual value. Example: 200 for a product page.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"checkText": {
"description": "Validate the rendered HTML once navigation completes. This is a substring check, not a waiter, and it doesn't poll. A missing substring returns an error envelope. Example: \"add to cart\" for a product page.",
"type": "string"
},
"cookies": {
"description": "Cookies to set before navigation: [{ name, value, domain? }]",
"items": {
"properties": {
"domain": {
"description": "Cookie domain (e.g. .example.com). Omit to scope it to the navigated URL's host.",
"type": "string"
},
"name": {
"description": "Cookie name.",
"type": "string"
},
"value": {
"description": "Cookie value.",
"type": "string"
}
},
"required": [
"name",
"value"
],
"type": "object"
},
"type": "array"
},
"headers": {
"additionalProperties": {
"type": "string"
},
"description": "Custom HTTP headers as a key-value object rather than [name, value] tuples. Example: {\"Referer\": \"https://google.com/\"}",
"propertyNames": {
"type": "string"
},
"type": "object"
},
"offload_large": {
"description": "If true, response bodies of 50 KB or more are returned as a resource_link instead of inlined. Default false. Read the returned offloaded_resource_uri with resources/read.",
"type": "boolean"
},
"proxy": {
"description": "Optional proxy. Three forms: (1) URL `http://user:pass@host:port` or `socks5://host:port`; (2) base36 ID from foura_proxy (e.g. `4DZ3VE`) to reuse the same exit; (3) omit to use the default route.",
"type": "string"
},
"timeout_ms": {
"description": "Page load timeout in ms (default 30000, max 120000)",
"maximum": 120000,
"minimum": 0,
"type": "integer"
},
"unblocker": {
"description": "Handle supported anti-bot or captcha challenges during navigation. Default true. Set false to return the page exactly as it loads, including any challenge page.",
"type": "boolean"
},
"url": {
"description": "Public URL to load in a full browser session. Private or reserved targets return `ssrf_blocked`. Example: https://shop.example.com/product/123.",
"format": "uri",
"type": "string"
},
"userAgent": {
"description": "Override the browser's User-Agent string",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "foura_browser",
"outputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"body": {
"anyOf": [
{
"type": "string"
},
{
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
}
],
"description": "Fully-rendered page content. String HTML when content-type is HTML; object when the page returned JSON and it was auto-parsed. Field is named `body`, not `data`. Omitted when offloaded."
},
"code": {
"description": "Stable error code for retry classification. auth_failed means the FourA API key was rejected; verify that key, not target-site credentials. Other codes: ssrf_blocked, upstream_non_json, output_validation_failed, bad_request (400), forbidden (403), not_found (404), rate_limited (429), at_capacity (503), service_disabled (503), service_unavailable (503), upstream_error (>=500), upstream_client_error (other 4xx), upstream_unknown (defensive).",
"type": "string"
},
"cookies": {
"description": "Full cookie objects collected after navigation, including name, value, domain, path, expiry, and same-site settings.",
"items": {
"additionalProperties": {},
"properties": {
"domain": {
"type": "string"
},
"expires": {
"type": "number"
},
"httpOnly": {
"type": "boolean"
},
"name": {
"type": "string"
},
"path": {
"type": "string"
},
"sameSite": {
"type": "string"
},
"secure": {
"type": "boolean"
},
"session": {
"type": "boolean"
},
"size": {
"type": "number"
},
"value": {
"type": "string"
}
},
"required": [
"name",
"value"
],
"type": "object"
},
"type": "array"
},
"current": {
"additionalProperties": false,
"properties": {
"concurrency": {
"type": "number"
},
"rpm": {
"type": "number"
}
},
"type": "object"
},
"error": {
"description": "Human-readable error message",
"type": "string"
},
"headers": {
"additionalProperties": {},
"description": "Response headers as a flat key-value object. Values are typically strings but may be arrays for repeated headers.",
"propertyNames": {
"type": "string"
},
"type": "object"
},
"limits": {
"additionalProperties": false,
"properties": {
"maxConcurrency": {
"type": "number"
},
"maxRpm": {
"type": "number"
}
},
"type": "object"
},
"offloaded_resource_uri": {
"description": "foura-mcp://payload/<uuid>. Pass this URI to resources/read to retrieve the offloaded body.",
"type": "string"
},
"retryAfter": {
"type": "number"
},
"service": {
"enum": [
"single",
"proxy",
"browser",
"api"
],
"type": "string"
},
"size_bytes": {
"description": "Total offloaded body size in bytes",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"status": {
"description": "HTTP status code from the target page. `0` indicates the navigation failed before any HTTP response (DNS / connection refused / timeout) - check the `error` field for the underlying reason.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"userAgent": {
"description": "The User-Agent the browser session presented",
"type": "string"
}
},
"type": "object"
},
"title": "FourA - full browser navigation"
},
{
"annotations": {
"destructiveHint": false,
"openWorldHint": true,
"readOnlyHint": true
},
"description": "Give it a public URL and get the content back. This is the default when you don't want to choose between HTTP, proxy rotation, and a full browser. On protected targets, or whenever HTTP 200 may still be a challenge or incomplete page, pass validate.data.accept with text unique to the real content. Auto makes bounded attempts and returns either validated content or a failure; it cannot guarantee a match. The response includes completion details and, by default, reusable session values for follow-up calls. Use a lower-level tool when you need direct control over HTTP, proxy selection, or browser navigation.",
"execution": {
"taskSupport": "forbidden"
},
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"data": {
"anyOf": [
{
"type": "string"
},
{
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
}
],
"description": "Request body for non-GET methods. Strings sent as-is; objects auto-serialized to JSON."
},
"followRedirects": {
"description": "Follow up to N redirects for HTTP and proxy requests. Default 5; 0 means don't follow. Browser navigation handles redirects itself.",
"maximum": 20,
"minimum": 0,
"type": "integer"
},
"forceProxy": {
"description": "Require proxy routing for every target request. Default true. Send false to allow direct HTTP when suitable.",
"type": "boolean"
},
"headers": {
"description": "Custom HTTP headers as [name, value] tuples. Example: [[\"Accept\", \"application/json\"], [\"Authorization\", \"Bearer ...\"]]",
"items": {
"items": [
{
"type": "string"
},
{
"type": "string"
}
],
"type": "array"
},
"type": "array"
},
"ignoreProxies": {
"description": "Exits to avoid - base36 proxy IDs (like \"4DZ3VE\") or proxy URLs. Use this to rotate away from an exit that was just blocked.",
"items": {
"type": "string"
},
"type": "array"
},
"method": {
"description": "HTTP method for the target request (default GET).",
"minLength": 1,
"type": "string"
},
"offload_large": {
"description": "If true, response bodies of 50 KB or more are returned as a resource_link instead of inlined. Default false. Read the returned offloaded_resource_uri with resources/read.",
"type": "boolean"
},
"returnSession": {
"description": "Return reusable {proxy, cookies, userAgent} values for follow-up calls. Default true. Send false for a leaner response when you only need the content.",
"type": "boolean"
},
"timeout_ms": {
"description": "Total time budget in ms for the whole operation. Every attempt must fit inside it. Default 120000, max 180000.",
"maximum": 180000,
"minimum": 5000,
"type": "integer"
},
"url": {
"description": "Public target URL. Private or reserved targets return `ssrf_blocked`. Use {ts} in the URL to insert the current Unix timestamp. Example: https://example.com/page.",
"format": "uri",
"type": "string"
},
"validate": {
"description": "Post-fetch response validation. When the response fails these checks foura_auto returns an error envelope.",
"properties": {
"data": {
"description": "Body validation: pass when the body contains an expected substring (accept), fail when it contains a blocked one (fail).",
"properties": {
"accept": {
"description": "Case-sensitive substrings the final body must contain. Use this on protected targets to distinguish the real page from a challenge page.",
"items": {
"type": "string"
},
"type": "array"
},
"fail": {
"description": "Substrings the final body must not contain",
"items": {
"type": "string"
},
"type": "array"
}
},
"type": "object"
},
"headers": {
"description": "Header validation: pass when an accepted header matches, fail when a blocklisted header matches.",
"properties": {
"accept": {
"additionalProperties": {
"type": "string"
},
"description": "Case-insensitive header substring rules. The response passes when at least one name/value pair matches.",
"propertyNames": {
"type": "string"
},
"type": "object"
},
"fail": {
"additionalProperties": {
"type": "string"
},
"description": "Case-insensitive header substring rules that reject the response when any name/value pair matches.",
"propertyNames": {
"type": "string"
},
"type": "object"
}
},
"type": "object"
},
"status": {
"description": "Status-code validation: which HTTP status codes count as success (accept) or failure (fail).",
"properties": {
"accept": {
"description": "HTTP status codes to treat as success",
"items": {
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"type": "array"
},
"fail": {
"description": "HTTP status codes to treat as failure",
"items": {
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"type": "array"
}
},
"type": "object"
}
},
"type": "object"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "foura_auto",
"outputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"attempts": {
"description": "Total attempts when the request failed (also present inside `meta`).",
"type": "number"
},
"code": {
"description": "Stable error code for retry classification. auth_failed means the FourA API key was rejected; verify that key, not target-site credentials. Other codes: ssrf_blocked, upstream_non_json, output_validation_failed, bad_request (400), forbidden (403), not_found (404), rate_limited (429), at_capacity (503), service_disabled (503), service_unavailable (503), upstream_error (>=500), upstream_client_error (other 4xx), upstream_unknown (defensive).",
"type": "string"
},
"current": {
"additionalProperties": false,
"description": "Caller's current usage at error time",
"properties": {
"concurrency": {
"type": "number"
},
"rpm": {
"type": "number"
}
},
"type": "object"
},
"data": {
"description": "Decoded response body of the delivered page. String by default; object when the body parsed as JSON. Omitted when offloaded."
},
"error": {
"description": "Human-readable error message when the request could not deliver content within the budget.",
"type": "string"
},
"headers": {
"anyOf": [
{
"items": {
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
}
]
},
"properties": {
"result": {
"additionalProperties": false,
"properties": {
"code": {
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"reason": {
"type": "string"
},
"version": {
"type": "string"
}
},
"type": "object"
}
},
"type": "object"
},
"type": "array"
},
{
"type": "string"
},
{
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
}
],
"description": "Response headers from the successful request, as an array of objects. Each entry has `result.{version, code, reason}` plus header-name keys. The last entry is the final response."
},
"limits": {
"additionalProperties": false,
"description": "Per-service limits at error time",
"properties": {
"maxConcurrency": {
"type": "number"
},
"maxRpm": {
"type": "number"
}
},
"type": "object"
},
"meta": {
"additionalProperties": {},
"description": "Completion details: rung, solved, attempts, and credits. Always present.",
"properties": {
"attempts": {
"description": "Total fetch attempts made for this request.",
"type": "number"
},
"credits": {
"description": "Total credits spent across all attempts.",
"type": "number"
},
"rung": {
"description": "Which method delivered the content (e.g. probe / proxy / browser / cache). `cache` means a reusable session was used.",
"type": "string"
},
"solved": {
"description": "True when a bot-defense was actively solved on the way to the content (vs. the target being open).",
"type": "boolean"
}
},
"type": "object"
},
"offloaded_resource_uri": {
"description": "foura-mcp://payload/<uuid>. Pass this URI to resources/read to retrieve the offloaded body.",
"type": "string"
},
"retryAfter": {
"description": "Seconds to wait before retrying a 429 or 503 response",
"type": "number"
},
"service": {
"enum": [
"single",
"proxy",
"browser",
"api",
"auto"
],
"type": "string"
},
"session": {
"additionalProperties": {},
"description": "Reusable {proxy, cookies, userAgent} values for follow-up calls. For plain HTTP, call foura_single with session.proxy as proxy, session.userAgent as a User-Agent header, and session.cookies serialized as a Cookie header. For JavaScript, pass the three values to foura_browser fields. Present by default; send returnSession:false to omit.",
"properties": {
"cookies": {
"description": "Cookie objects accumulated by the winning session. For foura_single, serialize their name/value pairs into a Cookie header; pass the array directly to foura_browser.cookies."
},
"proxy": {
"description": "Opaque base36 exit id of the session (e.g. `4DZ3VE`) - pass to foura_single.proxy / foura_proxy.proxy to replay through the same exit. Never a raw IP.",
"type": "string"
},
"userAgent": {
"description": "User-Agent used by the winning session. Send it as a User-Agent header to foura_single or as foura_browser.userAgent.",
"type": "string"
}
},
"type": "object"
},
"size_bytes": {
"description": "Total offloaded body size in bytes",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"status": {
"description": "HTTP status code from the request that delivered the content. `0` means no HTTP response was received; check `error`.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
}
},
"type": "object"
},
"title": "FourA - auto (smart fetch, picks the method for you)"
}
]
}
},
"url": "https://mcp.foura.ai/mcp"
},
"latency_ms": 389.68,
"status": "ok"
},
"transport_compliance_probe": {
"details": {
"bad_protocol_error": null,
"bad_protocol_headers": {
"content-type": "application/json; charset=utf-8",
"strict-transport-security": "max-age=31536000; includeSubDomains; preload"
},
"bad_protocol_payload": {
"error": {
"code": -32602,
"message": "Unsupported MCP-Protocol-Version: 1999-99-99. Supported (from @modelcontextprotocol/sdk): 2025-11-25, 2025-06-18, 2025-03-26, 2024-11-05, 2024-10-07. Upgrade foura-mcp's SDK pin to extend."
},
"id": null,
"jsonrpc": "2.0"
},
"bad_protocol_status_code": 400,
"delete_error": null,
"delete_status_code": null,
"expired_session_error": null,
"expired_session_status_code": null,
"issues": [
"missing_session_id",
"missing_protocol_header"
],
"last_event_id_visible": false,
"protocol_header_present": false,
"requested_protocol_version": "2025-03-26",
"session_id_present": false,
"transport": "streamable-http"
},
"latency_ms": 291.48,
"status": "warning"
},
"utility_coverage_probe": {
"details": {
"completions": {
"advertised": false,
"live_probe": "not_executed",
"sample_target": {
"argument_name": "url",
"name": "scrape_product_page",
"type": "prompt"
}
},
"initialize_capability_keys": [
"prompts",
"resources",
"tools"
],
"pagination": {
"metadata_signal": false,
"next_cursor_methods": [],
"supported": false
},
"tasks": {
"advertised": false,
"http_status": 200,
"probe_status": "missing"
}
},
"latency_ms": 97.73,
"status": "missing"
}
},
"failures": {
"oauth_authorization_server": {
"reason": "no_authorization_server"
},
"oauth_protected_resource": {
"error": "Client error '404 Not Found' for url 'https://mcp.foura.ai/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
"url": "https://mcp.foura.ai/.well-known/oauth-protected-resource"
},
"openid_configuration": {
"reason": "no_authorization_server"
},
"prompt_get": {
"headers": {
"content-type": "text/event-stream",
"strict-transport-security": "max-age=31536000; includeSubDomains; preload"
},
"http_status": 200,
"payload": {
"error": {
"code": -32602,
"message": "MCP error -32602: Invalid arguments for prompt scrape_product_page: [\n {\n \"expected\": \"string\",\n \"code\": \"invalid_type\",\n \"path\": [\n \"url\"\n ],\n \"message\": \"Invalid input: expected string, received undefined\"\n }\n]"
},
"id": 4,
"jsonrpc": "2.0"
},
"prompt_arguments": [
{
"description": "Product page URL (any e-commerce site)",
"name": "url",
"required": true
}
],
"prompt_name": "scrape_product_page",
"url": "https://mcp.foura.ai/mcp"
},
"server_card": {
"error": "Client error '404 Not Found' for url 'https://mcp.foura.ai/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
"url": "https://mcp.foura.ai/.well-known/mcp/server-card.json"
}
},
"remote_url": "https://mcp.foura.ai/mcp",
"server_card_payload": null,
"server_identifier": "ai.foura/mcp"
}
Known versions
0.5.0
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 08:50:49 PM UTC | Healthy | 74.0 | 3672.8 ms | 4 |
| Jul 31, 2026 06:38:06 AM UTC | Healthy | 43.1 | 3663.5 ms | 0 |
Validation timeline
| Validated | Summary | Score | Protocol | Auth mode | Tools | High-risk tools | Changes |
|---|---|---|---|---|---|---|---|
| Aug 04, 2026 08:50:49 PM UTC | Healthy | 74.0 | 2025-03-26 | public | 4 | 0 | auth_mode_changed write_surface_expanded tool_snapshot_changed |
| Jul 31, 2026 06:38:06 AM UTC | Healthy | 43.1 | unknown | unknown | 0 | 0 | none |
Recent validation runs
| Started | Status | Summary | Latency | Checks |
|---|---|---|---|---|
| Aug 04, 2026 08:50:46 PM UTC | Completed | Healthy | 3672.8 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 06:38:03 AM UTC | Completed | Healthy | 3663.5 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 08:50:49 PM UTC | Latest validation: healthy | Score 74.0 with status healthy. |
| Aug 04, 2026 08:50:49 PM UTC | Score changed | Score delta +30.8 versus the previous run. |
| Aug 04, 2026 08:50:49 PM UTC | Tool snapshot changed | Added 4, removed 0, and changed 0 tool contracts. |
| Aug 04, 2026 08:50:49 PM UTC | Auth mode changed | Auth mode moved from unknown to public. |
Capabilities
- OAuth:
- DCR/CIMD:
- Prompts:
- Homepage: https://foura.ai/mcp
- Docs: none
- Support: none
- Icon: none
- Remote endpoint: https://mcp.foura.ai/mcp
- Server card: none
Use-case taxonomy
development web automation
Benchmark tasks
| Benchmark task | Status | Evidence |
|---|---|---|
| Discover tools | Passes |
|
| Read-only fetch flow | Degraded |
|
| OAuth-required connect | Degraded |
|
| Safe write flow with confirmation | Likely to fail |
|
Utility coverage
Probe status
Missing
Completions
not detected
Completion probe target: {
"argument_name": "url",
"name": "scrape_product_page",
"type": "prompt"
}
Pagination
not detected
No nextCursor evidence.
Tasks
Missing
Advertised: no
Transport compliance drilldown
Probe status
Warning
Transport
streamable-http
Session header
no
Protocol header
no
Bad protocol response
400
DELETE teardown
n/a
Expired session retry
n/a
Last-Event-ID visible
no
Issues: missing_session_id, missing_protocol_header
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
foura_auto foura_browser foura_proxy foura_single
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
30.83
Summary changed
no
Tool delta
4
Prompt delta
6
Auth mode changed
yes
Write surface expanded
yes
Protocol regressed
no
Registry drift changed
no
Regressed checks: action_safety_probe, oauth_protected_resource, prompt_get, server_card
Improved checks: connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, official_registry_probe, probe_noise_resilience, prompts_list, provenance_divergence_probe, resources_list, tool_snapshot_probe, tools_list
| Component | Previous | Latest | Delta |
|---|---|---|---|
backward_compatibility_score | 2.0 | 4.0 | 2.0 |
trust_confidence_score | 1.75 | 2.94 | 1.19 |
advanced_capability_coverage_score | 3.0 | 1.88 | -1.12 |
connector_replay_score | 3.0 | 4.0 | 1.0 |
result_shape_stability_score | 3.0 | 4.0 | 1.0 |
tool_snapshot_churn_score | 3.0 | 4.0 | 1.0 |
utility_coverage_score | 2.0 | 1.0 | -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 public. - 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.foura/mcp |
official_registry | yes | 74.0 |
Alias consolidation
Canonical identifier
ai.foura/mcp
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
32/44
Connectivity, auth, and transport expectations for common clients.
Interface Quality
40.5/56
How well the tool/resource interface communicates and behaves under automation.
Security Posture
24/36
How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.
Reliability & Trust
20.94/24
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
2/4
Measures whether auth discovery and protected access behave predictably for clients.
Error Contract Quality
2.1/4
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
3/4
Availability, latency, and burst-failure profile across recent validation history.
Security Hygiene
3/4
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
3/4
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
4/4
Naming clarity, schema ergonomics, and parameter complexity across the tool surface.
Result Shape Stability
4/4
Stability of declared output schemas across validations, with penalties for drift or missing shapes.
OAuth Interop
3/4
Depth and client compatibility of OAuth/OIDC metadata beyond the minimal protected-resource check.
Recovery Semantics
1.5/4
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
2/4
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
2/4
Checks session headers, protocol-version enforcement, session teardown, and expired-session behavior.
Utility Coverage
1/4
Signals support for completions, pagination, and task-oriented utility surfaces that larger clients increasingly expect.
Advanced Capability Coverage
1.9/4
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
4/4
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
2.5/4
Assesses arbitrary URL fetch, crawl, webhook, and remote-request exposure on the tool surface.
Execution / Sandbox Safety
2.5/4
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
2/4
Rewards scoped auth metadata and penalizes broad or missing scopes around privileged tools.
Secret Handling Hygiene
2/4
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 | Expose /.well-known/oauth-protected-resource | Without a protected-resource document, OAuth clients cannot discover auth requirements reliably. | Serve /.well-known/oauth-protected-resource and point it at your authorization server metadata.Playbook
|
| High | Publish OAuth authorization-server metadata | Clients need authorization-server metadata to discover issuer, endpoints, and DCR support. | Publish /.well-known/oauth-authorization-server from your issuer and include registration_endpoint when supported.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 public. | 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 | Publish OpenID configuration | OIDC metadata improves token validation and client compatibility. | Expose /.well-known/openid-configuration with issuer, jwks_uri, and supported grants.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 | Expose modern utility surfaces like completions, pagination, or tasks | Utility coverage improves interoperability with larger clients and long-lived agent workflows. | Expose completions, pagination, and task metadata where supported so larger clients can plan and resume work safely.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 |
|---|---|---|
| Utility Coverage | 1/4 | -3.0 |
| Recovery Semantics | 1.5/4 | -2.5 |
| Advanced Capability Coverage | 1.9/4 | -2.1 |
| Transport Compliance | 2/4 | -2.0 |
| Spec Recency | 2/4 | -2.0 |
| Secret Handling Hygiene | 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 |
| Least Privilege Scope | 2/4 | -2.0 |
| Destructive Operation Safety | 2/4 | -2.0 |
Compatibility profiles
OpenAI Connectors
77.8
partial
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.
Connector URL: https://mcp.foura.ai/mcp # No OAuth metadata detected. # Server: ai.foura/mcp
Claude Desktop
100.0
compatible
No major blockers detected.
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.foura.ai/mcp"]
}
}
}
Smithery
100.0
compatible
No major blockers detected.
smithery mcp add "https://mcp.foura.ai/mcp"
Generic Streamable HTTP
100.0
compatible
No major blockers detected.
curl -sS https://mcp.foura.ai/mcp -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): 57.3 • 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 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.foura.ai/mcp # No OAuth metadata detected. # Server: ai.foura/mcp
Claude Desktop
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.foura.ai/mcp"]
}
}
}
Smithery
smithery mcp add "https://mcp.foura.ai/mcp"
Generic Http
curl -sS https://mcp.foura.ai/mcp -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
foura_single foura_proxy foura_browser foura_auto
Observed from the latest live validation against https://mcp.foura.ai/mcp. This is the target server surface, not Verify's own inspection tools.
Live capability counts
4 tools • 6 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.foura/mcp.Direct machine links