ai.justpublish/just-publish
Just Publish
Publish the website you built with AI to a live public URL — straight from chat, no setup.
DECISION SUMMARY
Block For Production
Score
65.6
Rank suppressed while production readiness shows a blocking verdict.
Confidence
High
Based on evidence completeness, recency, and validation density.
Evidence age
9.9h old
Freshness: fresh. Snapshot
trustsnap_7da76e60cc826e36.Top risk drivers
- Utility Coverage
- Step Up Auth
- Request Association
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.
- Serve /.well-known/oauth-protected-resource and point it at your authorization server metadata.
Next action
revalidate, add safeguards, export policy
write/admin actions need confirmation safeguards + high-risk tools need review
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
65.6
Transport
streamable-http
Tools
3
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
3
High-risk tools
2
Destructive tools
0
Exec tools
0
Egress tools
2
Secret tools
3
Bulk-access tools
0
Risk distribution
medium:1, high:2
Tool capability & risk inventory
| Tool | Capabilities | Risk | Findings | Notes |
|---|---|---|---|---|
deploy |
write network secrets | High | arbitrary network egress secret material access | No explicit safeguard hints detected. |
get_site_files |
read secrets | Medium | secret material access | No explicit safeguard hints detected. |
update_site_file |
write network secrets | High | arbitrary network egress secret material access | No explicit safeguard hints detected. |
Write-action governance
Governance status
Error
Safe to publish
Auth boundary
public_or_unclear
Blast radius
Medium
High-risk tools
2
Confirmation signals
none
Safeguard count
0
Status detail: 2 high-risk tool(s) are exposed without a clear auth boundary; no safeguards or confirmation signals detected.
| Tool | Risk | Flags | Safeguards |
|---|---|---|---|
deploy |
High | arbitrary network egress secret material access | no |
update_site_file |
High | arbitrary network egress secret material access | no |
Action-controls diff
Snapshot changed
yes
Disabled-by-default candidates
deploy update_site_file
Manual review candidates
deploy update_site_file
New actions
| Action | Risk | Flags |
|---|---|---|
deploy | High | arbitrary network egress secret material access |
get_site_files | Medium | secret material access |
update_site_file | High | arbitrary network egress secret material access |
Changed actions
| Action | Change types | Risk |
|---|---|---|
| No materially changed actions. | ||
Critical alerts
High/critical-severity alerts
3
Production verdicts degrade quickly when high or critical-severity 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.; Transport compliance failed or did not complete successfully.; OAuth interoperability should be strong.
Confidence: high (87.5)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
initialize• OKtools_list• OKtransport_compliance_probe• Errorstep_up_auth_probe• 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
Transport behavior should match Claude-compatible HTTP expectations.
Confidence: high (87.5)
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 blocked
action_safety_probe reported an unconfirmed high-risk, destructive, or exec-capable tool. Risky write actions are present without a clear auth boundary and confirmation signal. Active alert(s) affecting production readiness: Tool snapshot changed, Auth mode changed, Write-action surface expanded.
Confidence: high (87.5)
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 (87.5)
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.Transport compliance failed or did not complete successfully.OAuth interoperability should be strong.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.
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.OAuth is not configured, so this client cannot authenticate without additional setup.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 export, bulk, mutating, or high-blast-radius exposure.
Write-safe publishing
Blocked
Remediation checklist
Add a clearer auth boundary around risky write actions.Add confirmation or dry-run semantics for: deploy, update_site_file.The write/destructive action surface just expanded since the last validation -- review before publishing.Production readiness is blocked by an active alert: Tool snapshot changed.Production readiness is blocked by an active alert: Auth mode changed.Production readiness is blocked by an active alert: Write-action surface expanded.
Verdict traces
Production verdict
Needs remediation
Degraded from Safe for evaluation: 3 open high/critical-severity alert(s) are active, including at least one that blocks even evaluation-level trust.
Confidence: high (87.5)
Winning source: live_validation
Triggering alerts
server_card_schema_drifted• medium • Server card and live tool schemas disagreetool_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.; Transport compliance failed or did not complete successfully.; OAuth interoperability should be strong. Compatibility is not a production approval; company knowledge and Messages API gates remain separate.
- Search Fetch Only: No
- Write Actions Present: Yes
- Oauth Configured: No
- 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: No
- Admin Refresh Required: Yes
- Safe For Company Knowledge: No
- 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.; Transport compliance failed or did not complete successfully.; OAuth interoperability should be strong.
- remote_http_endpoint: Passes
- oauth_discovery: Degraded
- 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: Degraded
Recommended for
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_7da76e60cc826e36Use this ID to compare server page, report, policy, MCP, homepage, ranking, and shortlist surfaces.
Snapshot generated
Aug 09, 2026 05:21:15 PM UTC
All page, report, policy, and MCP surfaces use this same server-detail snapshot shape.
Last validated
Aug 09, 2026 07:28:35 AM UTC
Age: 9.88h • evidence age tier: Verified in last 24h • display score: 65.62
Canonical machine links
Compare index
Policy export
Badge metadata
Ledger evidence
Human compare URL
Evidence confidence
Confidence score
87.5
Based on 10 recent validations, 27 captured checks, and validation age of 9.9 hours.
Live checks captured
27
More direct checks increase trust in the current verdict.
Validation age
9.9h
Lower age means fresher evidence.
Latest validation evidence
Latest summary
Healthy
Validation profile
remote_mcp
Started
Aug 09, 2026 07:28:34 AM UTC
Latency
1097.9 ms
Failures
oauth_authorization_serverno authorization serveroauth_protected_resourceClient error '404 Not Found' for url 'https://mcp.justpublish.ai/.well-known/oauth-protected-resource' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404openid_configurationno authorization servertransport_compliance_probeIssues: missing protocol header, bad protocol not rejected, delete session unexpected, expired session not 404 (bad protocol=200, DELETE=405, expired session=200).
Checks
| Check | Status | Latency | Evidence |
|---|---|---|---|
action_safety_probe |
Error | n/a | 2 high-risk tool(s); no clear auth boundary; safeguards=0; confirmation=none. |
advanced_capabilities_probe |
OK | n/a | 4 capability signal(s): prompts, resource links, resources, structured outputs. |
connector_publishability_probe |
Warning | n/a | Publishability blockers: transport compliance, action safety. |
connector_replay_probe |
OK | n/a | Backward compatible with no breaking tool-surface changes. |
determinism_probe |
OK | 76.1 ms | Check completed |
initialize |
OK | 102.9 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 | 9.9 ms | Client error '404 Not Found' for url 'https://mcp.justpublish.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 | 112.7 ms | Fetched https://mcp.justpublish.ai/robots.txt |
prompt_get |
Missing | n/a | no prompt name |
prompts_list |
OK | 78.1 ms | 0 prompt(s) exposed |
protocol_version_probe |
Warning | n/a | Claims 2025-03-26; 2 release(s) behind 2025-11-25. |
provenance_divergence_probe |
Not_Assessed | n/a | Check completed |
request_association_probe |
Missing | n/a | No request-association capabilities were advertised. |
resource_read |
OK | 114.0 ms | 1 resource content item(s) returned |
resources_list |
OK | 107.2 ms | 5 resource item(s) exposed |
schema_divergence_probe |
Warning | n/a | Check completed |
server_card |
OK | 9.8 ms | $schema, authentication, capabilities, description |
session_resume_probe |
OK | 119.3 ms | 3 tool(s) exposed |
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 | 121.5 ms | 3 tool(s) exposed |
transport_compliance_probe |
Error | 48.5 ms | Issues: missing protocol header, bad protocol not rejected, delete session unexpected, expired session not 404 (bad protocol=200, DELETE=405, expired session=200). |
utility_coverage_probe |
Missing | 24.2 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": [],
"reason": null,
"safeguard_count": 0,
"summary": {
"annotation_conflict_tools": 1,
"bulk_access_tools": 0,
"capability_distribution": {
"network": 2,
"read": 1,
"secrets": 3,
"write": 2
},
"declared_non_read_only_tools": 2,
"destructive_tools": 0,
"egress_tools": 2,
"exec_tools": 0,
"has_mutating_capability": true,
"has_non_read_capability": true,
"high_risk_tools": 2,
"risk_distribution": {
"critical": 0,
"high": 2,
"low": 0,
"medium": 1
},
"secret_tools": 3,
"tool_count": 3
}
},
"latency_ms": null,
"status": "error"
},
"advanced_capabilities_probe": {
"details": {
"capabilities": {
"completions": false,
"elicitation": false,
"prompts": true,
"resource_links": true,
"resources": true,
"roots": false,
"sampling": false,
"structured_outputs": true
},
"enabled": [
"prompts",
"resource_links",
"resources",
"structured_outputs"
],
"enabled_count": 4,
"initialize_capability_keys": [
"resources",
"tools"
]
},
"latency_ms": null,
"status": "ok"
},
"connector_publishability_probe": {
"details": {
"blockers": [
"transport_compliance",
"action_safety"
],
"criteria": {
"action_safety": false,
"auth_flow": true,
"connector_replay": true,
"initialize": true,
"protocol_version": true,
"remote_transport": true,
"request_association": true,
"server_card": true,
"session_resume": true,
"step_up_auth": true,
"tool_surface": true,
"tools_list": true,
"transport_compliance": false
},
"high_risk_tools": 2,
"tool_count": 3,
"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": "416abaf688db54ab4690a910680223b997740dfb5d446894623b0624e2c20452",
"errors": [],
"matches": 2,
"stable_ratio": 1.0,
"successful": 2
},
"latency_ms": 76.14,
"status": "ok"
},
"initialize": {
"details": {
"headers": {
"content-type": "text/event-stream",
"mcp-session-id": "8fdf22ade1cdf4d67fdfdb66d1c6f385"
},
"http_status": 200,
"payload": {
"id": 1,
"jsonrpc": "2.0",
"result": {
"capabilities": {
"resources": {},
"tools": {}
},
"instructions": "Publish the website you built with AI to a live public URL \u2014 straight from chat, no setup.",
"protocolVersion": "2025-03-26",
"serverInfo": {
"description": "Publish the website you built with AI to a live public URL \u2014 straight from chat, no setup.",
"icons": [
{
"mimeType": "image/png",
"sizes": [
"512x512"
],
"src": "https://justpublish.ai/icon.png"
},
{
"mimeType": "image/png",
"sizes": [
"192x192"
],
"src": "https://justpublish.ai/icon-192.png"
}
],
"name": "Just Publish",
"title": "Just Publish",
"version": "0.1.5",
"websiteUrl": "https://justpublish.ai"
}
}
},
"url": "https://mcp.justpublish.ai/"
},
"latency_ms": 102.88,
"status": "ok"
},
"interactive_flow_probe": {
"details": {
"oauth_supported": false,
"prompt_available": false,
"risk_hits": [],
"safe_hits": [
"login"
]
},
"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.justpublish.ai/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
"url": "https://mcp.justpublish.ai/.well-known/oauth-protected-resource"
},
"latency_ms": 9.94,
"status": "error"
},
"official_registry_probe": {
"details": {
"direct_match": true,
"official_peer_count": 1,
"registry_identifier": "ai.justpublish/just-publish",
"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;charset=UTF-8"
},
"http_status": 404,
"url": "https://mcp.justpublish.ai/robots.txt",
"validation_disallowed": false
},
"latency_ms": 112.7,
"status": "ok"
},
"prompt_get": {
"details": {
"reason": "no_prompt_name"
},
"latency_ms": null,
"status": "missing"
},
"prompts_list": {
"details": {
"headers": {
"content-type": "text/event-stream",
"mcp-session-id": "b5eee6db3c806bb1ebab2ab6b4b65cbe"
},
"http_status": 200,
"payload": {
"id": 3,
"jsonrpc": "2.0",
"result": {
"prompts": []
}
},
"url": "https://mcp.justpublish.ai/"
},
"latency_ms": 78.1,
"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": {
"comparable_field_count": 0,
"compared_fields": [
"title",
"version",
"homepage",
"repository"
],
"direct_official_match": true,
"drift_fields": [],
"metadata_document_count": 3,
"readable_sources": [
"registry",
"server_card"
],
"registry_homepage": null,
"registry_repository": null,
"registry_title": null,
"registry_version": null,
"server_card_homepage": null,
"server_card_repository": "https://github.com/just-done/just-publish-mcp",
"server_card_title": "Just Publish",
"server_card_version": "0.1.5"
},
"latency_ms": null,
"status": "not_assessed"
},
"request_association_probe": {
"details": {
"reason": "no_request_association_capabilities_advertised"
},
"latency_ms": null,
"status": "missing"
},
"resource_read": {
"details": {
"headers": {
"content-type": "text/event-stream",
"mcp-session-id": "e5a956e92aba194e3d88f2eadffd9ad0"
},
"http_status": 200,
"payload": {
"id": 6,
"jsonrpc": "2.0",
"result": {
"contents": [
{
"mimeType": "text/markdown",
"text": "# Just Publish\n\nJust Publish turns a set of static files (HTML/CSS/JS/images) into a live,\npublic website. No build step, no framework, no login, no git \u2014 files in, URL\nout. The user does not need an account; publishing only needs their email\n(captured unverified, used for recovery and to claim the site).\n\nLive sites are served at `https://{site_id}.justpublish.site/`.\n\n## Which tool to use\n\n- **deploy** \u2014 publish a NEW site, OR fully REPLACE an existing site's files.\n On update, any file you DON'T include is deleted. Use it for the first\n publish and for wholesale rewrites.\n- **get_site_files** \u2014 read what's currently live (manifest + text file\n contents + the site's version). Use it before editing so you change the real\n current file instead of regenerating from memory.\n- **update_site_file** \u2014 change ONE or a FEW files; everything else is left\n exactly as it was (MERGE). Use it for targeted edits (fix a typo, swap a\n stylesheet, add a page).\n\n## The golden rule for edits\n\nWhen the user asks to *change* an existing site, prefer:\nget_site_files \u2192 edit the returned content \u2192 update_site_file (with\nexpected_version). This preserves the user's other files and any hand-edits.\nOnly reach for deploy-as-update when you intend to replace the whole site.\n",
"uri": "https://justpublish.ai/.well-known/mcp/overview.md"
}
]
}
},
"resource_uri": "https://justpublish.ai/.well-known/mcp/overview.md",
"url": "https://mcp.justpublish.ai/"
},
"latency_ms": 114.04,
"status": "ok"
},
"resources_list": {
"details": {
"headers": {
"content-type": "text/event-stream",
"mcp-session-id": "d2dfd66dc59c65d453c85c94a6800334"
},
"http_status": 200,
"payload": {
"id": 5,
"jsonrpc": "2.0",
"result": {
"resources": [
{
"annotations": {
"audience": [
"assistant"
],
"priority": 0.9
},
"description": "One-screen orientation: Just Publish turns static files into a live public URL with no build, no login, no git. Explains when to use deploy vs. get_site_files vs. update_site_file.",
"mimeType": "text/markdown",
"name": "just-publish-overview",
"title": "Just Publish \u2014 what it is and which tool to use",
"uri": "https://justpublish.ai/.well-known/mcp/overview.md"
},
{
"annotations": {
"audience": [
"assistant"
],
"priority": 1
},
"description": "The recommended loop for changing an existing site: get_site_files to read current state + version, edit, update_site_file with expected_version. Covers conflicts and when to fall back to deploy.",
"mimeType": "text/markdown",
"name": "just-publish-edit-lifecycle",
"title": "Edit lifecycle \u2014 read \u2192 edit \u2192 update, safely",
"uri": "https://justpublish.ai/.well-known/mcp/edit-lifecycle.md"
},
{
"annotations": {
"audience": [
"assistant"
],
"priority": 0.7
},
"description": "Rules for the files array: relative paths only (no .., no leading /), text vs. base64 encoding, per-file and per-site size caps, routing (/foo \u2192 /foo/index.html).",
"mimeType": "text/markdown",
"name": "just-publish-file-conventions",
"title": "File conventions \u2014 paths, encodings, limits",
"uri": "https://justpublish.ai/.well-known/mcp/file-conventions.md"
},
{
"annotations": {
"audience": [
"assistant"
],
"priority": 0.8
},
"description": "Non-negotiables: every site needs index.html at root; deploy REPLACES all files (omitted = deleted) while update_site_file MERGES; the edit_token is the only way to change a site and must be saved.",
"mimeType": "text/markdown",
"name": "just-publish-invariants",
"title": "Hard invariants you must respect",
"uri": "https://justpublish.ai/.well-known/mcp/invariants.md"
},
{
"description": "Inline UI shown after deploy: a live-going-up animation, the live site URL with a \"View your site\" button, and (for a freshly published site) a gentle verify-your-email step.",
"mimeType": "text/html;profile=mcp-app",
"name": "just-publish-publish-moment",
"title": "Publish moment \u2014 live URL + verify",
"uri": "ui://just-publish/publish-moment-v1.html"
}
]
}
},
"url": "https://mcp.justpublish.ai/"
},
"latency_ms": 107.22,
"status": "ok"
},
"schema_divergence_probe": {
"details": {
"auth_scheme_mismatch": false,
"card_auth_schemes": [],
"card_server_name": "Just Publish",
"card_server_version": "0.1.5",
"compared_dimensions": [
"server_name",
"server_version",
"declared_vs_observed_auth",
"tool_membership",
"parameter_names",
"required_parameters",
"parameter_types",
"output_schema_presence"
],
"compared_tool_count": 3,
"live_oauth_observed": false,
"live_server_name": "Just Publish",
"live_server_version": "0.1.5",
"server_name_mismatch": false,
"server_version_mismatch": false,
"severity": "medium",
"tool_divergences": [
{
"output_schema_card_declared": false,
"output_schema_live_declared": true,
"tool": "deploy"
},
{
"output_schema_card_declared": false,
"output_schema_live_declared": true,
"tool": "get_site_files"
},
{
"output_schema_card_declared": false,
"output_schema_live_declared": true,
"tool": "update_site_file"
}
],
"tools_missing_from_card": [],
"tools_missing_from_live": [],
"tools_with_omitted_schema": [
"deploy",
"get_site_files",
"update_site_file"
]
},
"latency_ms": null,
"status": "warning"
},
"server_card": {
"details": {
"headers": {
"content-type": "application/json; charset=utf-8"
},
"http_status": 200,
"payload": {
"$schema": "https://static.modelcontextprotocol.io/schemas/v1/server-card.schema.json",
"authentication": {
"required": false
},
"capabilities": {
"prompts": false,
"resources": true,
"tools": true
},
"description": "Publish the website you built with AI to a live public URL \u2014 straight from chat, no setup.",
"icons": [
{
"mimeType": "image/png",
"sizes": [
"512x512"
],
"src": "https://justpublish.ai/icon.png"
},
{
"mimeType": "image/png",
"sizes": [
"192x192"
],
"src": "https://justpublish.ai/icon-192.png"
}
],
"name": "ai.justpublish/just-publish",
"protocolVersion": "2025-11-25",
"remotes": [
{
"supportedProtocolVersions": [
"2025-11-25",
"2025-06-18",
"2025-03-26",
"2024-11-05"
],
"type": "streamable-http",
"url": "https://mcp.justpublish.ai/"
}
],
"repository": {
"source": "github",
"url": "https://github.com/just-done/just-publish-mcp"
},
"serverInfo": {
"description": "Publish the website you built with AI to a live public URL \u2014 straight from chat, no setup.",
"name": "Just Publish",
"version": "0.1.5"
},
"serverUrl": "https://mcp.justpublish.ai/",
"title": "Just Publish",
"tools": [
{
"description": "Put a website live at a public URL from static files (HTML/CSS/JS/images). Returns a working URL, a site_id, and an edit_token. No build step, no login.",
"name": "deploy"
},
{
"description": "Read the files currently live on a site (needs its site_id + edit_token) before editing.",
"name": "get_site_files"
},
{
"description": "Change one or a few files on an existing site in place, without republishing the whole site.",
"name": "update_site_file"
}
],
"transport": {
"endpoint": "https://mcp.justpublish.ai/",
"type": "streamable-http"
},
"version": "0.1.5",
"websiteUrl": "https://justpublish.ai"
},
"url": "https://mcp.justpublish.ai/.well-known/mcp/server-card.json"
},
"latency_ms": 9.85,
"status": "ok"
},
"session_resume_probe": {
"details": {
"headers": {
"content-type": "text/event-stream",
"mcp-session-id": "8fdf22ade1cdf4d67fdfdb66d1c6f385"
},
"http_status": 200,
"payload": {
"id": 301,
"jsonrpc": "2.0",
"result": {
"tools": [
{
"_meta": {
"openai/outputTemplate": "ui://just-publish/publish-moment-v1.html",
"openai/toolInvocation/invoked": "Your site is live",
"openai/toolInvocation/invoking": "Publishing your site\u2026",
"openai/widgetCSP": {
"redirect_domains": [
"https://justpublish.site",
"https://justpublish.ai"
]
},
"ui": {
"resourceUri": "ui://just-publish/publish-moment-v1.html"
}
},
"annotations": {
"destructiveHint": false,
"openWorldHint": true,
"readOnlyHint": false,
"title": "Publish a website"
},
"description": "Put a website live at a public URL. Use this when the user wants to publish, launch, or get a page online \u2014 e.g. 'I need a website', 'put up a page for my business', 'make this live'. Takes static files (HTML, CSS, JS, images) and returns a working URL anyone can open. No build step, no config. First call: omit site_id and edit_token \u2014 you get back a url, a site_id, and an edit_token. Keep the edit_token; it's the only way to change this site later. Later calls: pass site_id + edit_token to publish over the same site. deploy REPLACES the whole site \u2014 any file you leave out is DELETED. To change just one or a few files, use update_site_file instead. To see what's currently live before editing, use get_site_files first.",
"inputSchema": {
"properties": {
"edit_token": {
"description": "Edit token returned at create time. Required to update.",
"type": "string"
},
"email": {
"description": "Email to associate with the site. Captured unverified at first deploy; verification only required later for custom domains and recovery.",
"type": "string"
},
"files": {
"description": "Files to publish. Must include an index.html at the root.",
"items": {
"properties": {
"content": {
"description": "File body. Text by default; binary must be base64.",
"type": "string"
},
"encoding": {
"description": "Defaults to utf-8 for text extensions, base64 otherwise.",
"enum": [
"base64",
"utf-8"
],
"type": "string"
},
"path": {
"description": "Path under the site root, e.g. 'index.html', 'assets/logo.png'.",
"type": "string"
}
},
"required": [
"path",
"content"
],
"type": "object"
},
"minItems": 1,
"type": "array"
},
"site_id": {
"description": "Existing site id to update. Omit to create a new site.",
"type": "string"
}
},
"required": [
"files",
"email"
],
"type": "object"
},
"name": "deploy",
"outputSchema": {
"properties": {
"created": {
"description": "true if this call created a new site; false if it updated an existing one.",
"type": "boolean"
},
"dashboard_url": {
"description": "Deep link to this site in the owner's dashboard.",
"type": "string"
},
"edit_token": {
"description": "Returned ONLY on first create. Save it \u2014 it's the only way to update this site.",
"type": "string"
},
"email_masked": {
"description": "The owner email, masked for display (e.g. 'a***@example.com').",
"type": "string"
},
"email_verified": {
"description": "Whether the site's owner email is verified right now. New sites are always false.",
"type": "boolean"
},
"files_uploaded": {
"description": "Number of files written in this deploy.",
"type": "integer"
},
"site_id": {
"description": "The site's slug / id \u2014 pass back to update it later.",
"type": "string"
},
"total_bytes": {
"description": "Total size of the site in bytes after this deploy.",
"type": "integer"
},
"url": {
"description": "The live URL of the published site.",
"type": "string"
},
"verify_required": {
"description": "true when the owner still needs to verify their email (keys on !email_verified).",
"type": "boolean"
}
},
"required": [
"url",
"site_id",
"created",
"email_verified",
"files_uploaded",
"total_bytes",
"email_masked",
"verify_required",
"dashboard_url"
],
"type": "object"
}
},
{
"annotations": {
"destructiveHint": false,
"openWorldHint": false,
"readOnlyHint": true,
"title": "Read a published site's files"
},
"description": "Read the files of a site you already published, so you can make a targeted edit instead of rebuilding the whole site from memory. Returns a complete manifest (every file's path, size, content-type, sha256) plus the contents of the text files (HTML/CSS/JS/etc). Also returns the site's current `version` \u2014 pass it back to update_site_file so you don't overwrite a newer change. Pass `paths` to fetch only specific files; omit it to get all text files. Requires site_id + edit_token.",
"inputSchema": {
"properties": {
"edit_token": {
"description": "The edit token returned at publish time.",
"type": "string"
},
"paths": {
"description": "Optional. Specific file paths to return contents for (e.g. ['index.html','style.css']). Omit to get all text files. The manifest always lists every file regardless.",
"items": {
"type": "string"
},
"type": "array"
},
"site_id": {
"description": "The site id returned at publish time.",
"type": "string"
}
},
"required": [
"site_id",
"edit_token"
],
"type": "object"
},
"name": "get_site_files",
"outputSchema": {
"properties": {
"files": {
"description": "Inlined contents of the requested text files (default: all text files, capped for size).",
"items": {
"properties": {
"content": {
"description": "Full text content of the file.",
"type": "string"
},
"encoding": {
"description": "Always 'utf-8' \u2014 only text files are inlined.",
"enum": [
"utf-8"
],
"type": "string"
},
"path": {
"description": "Path of this file under the site root.",
"type": "string"
}
},
"required": [
"path",
"content",
"encoding"
],
"type": "object"
},
"type": "array"
},
"manifest": {
"description": "Every file on the site (always complete, regardless of which contents were inlined).",
"items": {
"properties": {
"content_type": {
"description": "Stored content-type, e.g. 'text/html'.",
"type": "string"
},
"is_text": {
"description": "Whether the file is a text type eligible to have its content inlined.",
"type": "boolean"
},
"path": {
"description": "Path under the site root, e.g. 'index.html'.",
"type": "string"
},
"sha256": {
"description": "Hex sha256 of the file bytes; null if not recorded for this file.",
"type": [
"string",
"null"
]
},
"size_bytes": {
"description": "File size in bytes.",
"type": "integer"
}
},
"required": [
"path",
"size_bytes",
"content_type",
"sha256",
"is_text"
],
"type": "object"
},
"type": "array"
},
"site_id": {
"description": "The site's slug / id.",
"type": "string"
},
"truncated": {
"description": "true if some requested file contents were omitted for size \u2014 request specific paths to read them.",
"type": "boolean"
},
"url": {
"description": "The live URL of the site.",
"type": "string"
},
"version": {
"description": "The site's current version \u2014 pass as expected_version to update_site_file to avoid clobbering.",
"type": "integer"
}
},
"required": [
"site_id",
"version",
"url",
"manifest",
"files",
"truncated"
],
"type": "object"
}
},
{
"annotations": {
"destructiveHint": false,
"openWorldHint": true,
"readOnlyHint": false,
"title": "Edit specific files of a published site"
},
"description": "Change one or a few files of an already-published site, leaving every other file untouched (a merge \u2014 unlike deploy, which replaces the whole site). Ideal for small edits: fix a typo in index.html, swap a stylesheet, add one page. Best practice: call get_site_files first, edit the returned content, then call this with the files you changed and the `expected_version` from that read \u2014 if the site changed in the meantime you get a clear conflict telling you to re-read. Requires site_id + edit_token. Cannot delete files (use deploy to drop a file) and cannot remove index.html.",
"inputSchema": {
"properties": {
"edit_token": {
"description": "The edit token returned at publish time.",
"type": "string"
},
"expected_version": {
"description": "Optional but recommended. The `version` you got from get_site_files. If the site has changed since, the update is rejected with a conflict so you can re-read and re-apply. Omit to force last-writer-wins.",
"type": "integer"
},
"files": {
"description": "The files to change. Only these are written; all other files on the site survive.",
"items": {
"properties": {
"content": {
"description": "Full new file body. Text by default; binary must be base64.",
"type": "string"
},
"encoding": {
"description": "Defaults to utf-8 for text, base64 otherwise.",
"enum": [
"base64",
"utf-8"
],
"type": "string"
},
"path": {
"description": "Path under the site root, e.g. 'index.html'.",
"type": "string"
}
},
"required": [
"path",
"content"
],
"type": "object"
},
"minItems": 1,
"type": "array"
},
"site_id": {
"description": "The site id returned at publish time.",
"type": "string"
}
},
"required": [
"site_id",
"edit_token",
"files"
],
"type": "object"
},
"name": "update_site_file",
"outputSchema": {
"properties": {
"files_total": {
"description": "Total number of files on the site after the merge.",
"type": "integer"
},
"files_written": {
"description": "Paths of the files written in this update. All other files were left untouched.",
"items": {
"type": "string"
},
"type": "array"
},
"site_id": {
"description": "The site's slug / id.",
"type": "string"
},
"url": {
"description": "The live URL of the site.",
"type": "string"
},
"version": {
"description": "The site's new version after the merge.",
"type": "integer"
}
},
"required": [
"site_id",
"url",
"version",
"files_written",
"files_total"
],
"type": "object"
}
}
]
}
},
"requested_protocol_version": "2025-03-26",
"resumed": true,
"session_id_present": true,
"transport": "streamable-http",
"url": "https://mcp.justpublish.ai/"
},
"latency_ms": 119.33,
"status": "ok"
},
"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": 3,
"previous_tool_count": 3,
"removed": [],
"similarity": 1.0
},
"latency_ms": null,
"status": "ok"
},
"tools_list": {
"details": {
"headers": {
"content-type": "text/event-stream",
"mcp-session-id": "149301aa7511377f9b9e937d08834165"
},
"http_status": 200,
"payload": {
"id": 2,
"jsonrpc": "2.0",
"result": {
"tools": [
{
"_meta": {
"openai/outputTemplate": "ui://just-publish/publish-moment-v1.html",
"openai/toolInvocation/invoked": "Your site is live",
"openai/toolInvocation/invoking": "Publishing your site\u2026",
"openai/widgetCSP": {
"redirect_domains": [
"https://justpublish.site",
"https://justpublish.ai"
]
},
"ui": {
"resourceUri": "ui://just-publish/publish-moment-v1.html"
}
},
"annotations": {
"destructiveHint": false,
"openWorldHint": true,
"readOnlyHint": false,
"title": "Publish a website"
},
"description": "Put a website live at a public URL. Use this when the user wants to publish, launch, or get a page online \u2014 e.g. 'I need a website', 'put up a page for my business', 'make this live'. Takes static files (HTML, CSS, JS, images) and returns a working URL anyone can open. No build step, no config. First call: omit site_id and edit_token \u2014 you get back a url, a site_id, and an edit_token. Keep the edit_token; it's the only way to change this site later. Later calls: pass site_id + edit_token to publish over the same site. deploy REPLACES the whole site \u2014 any file you leave out is DELETED. To change just one or a few files, use update_site_file instead. To see what's currently live before editing, use get_site_files first.",
"inputSchema": {
"properties": {
"edit_token": {
"description": "Edit token returned at create time. Required to update.",
"type": "string"
},
"email": {
"description": "Email to associate with the site. Captured unverified at first deploy; verification only required later for custom domains and recovery.",
"type": "string"
},
"files": {
"description": "Files to publish. Must include an index.html at the root.",
"items": {
"properties": {
"content": {
"description": "File body. Text by default; binary must be base64.",
"type": "string"
},
"encoding": {
"description": "Defaults to utf-8 for text extensions, base64 otherwise.",
"enum": [
"base64",
"utf-8"
],
"type": "string"
},
"path": {
"description": "Path under the site root, e.g. 'index.html', 'assets/logo.png'.",
"type": "string"
}
},
"required": [
"path",
"content"
],
"type": "object"
},
"minItems": 1,
"type": "array"
},
"site_id": {
"description": "Existing site id to update. Omit to create a new site.",
"type": "string"
}
},
"required": [
"files",
"email"
],
"type": "object"
},
"name": "deploy",
"outputSchema": {
"properties": {
"created": {
"description": "true if this call created a new site; false if it updated an existing one.",
"type": "boolean"
},
"dashboard_url": {
"description": "Deep link to this site in the owner's dashboard.",
"type": "string"
},
"edit_token": {
"description": "Returned ONLY on first create. Save it \u2014 it's the only way to update this site.",
"type": "string"
},
"email_masked": {
"description": "The owner email, masked for display (e.g. 'a***@example.com').",
"type": "string"
},
"email_verified": {
"description": "Whether the site's owner email is verified right now. New sites are always false.",
"type": "boolean"
},
"files_uploaded": {
"description": "Number of files written in this deploy.",
"type": "integer"
},
"site_id": {
"description": "The site's slug / id \u2014 pass back to update it later.",
"type": "string"
},
"total_bytes": {
"description": "Total size of the site in bytes after this deploy.",
"type": "integer"
},
"url": {
"description": "The live URL of the published site.",
"type": "string"
},
"verify_required": {
"description": "true when the owner still needs to verify their email (keys on !email_verified).",
"type": "boolean"
}
},
"required": [
"url",
"site_id",
"created",
"email_verified",
"files_uploaded",
"total_bytes",
"email_masked",
"verify_required",
"dashboard_url"
],
"type": "object"
}
},
{
"annotations": {
"destructiveHint": false,
"openWorldHint": false,
"readOnlyHint": true,
"title": "Read a published site's files"
},
"description": "Read the files of a site you already published, so you can make a targeted edit instead of rebuilding the whole site from memory. Returns a complete manifest (every file's path, size, content-type, sha256) plus the contents of the text files (HTML/CSS/JS/etc). Also returns the site's current `version` \u2014 pass it back to update_site_file so you don't overwrite a newer change. Pass `paths` to fetch only specific files; omit it to get all text files. Requires site_id + edit_token.",
"inputSchema": {
"properties": {
"edit_token": {
"description": "The edit token returned at publish time.",
"type": "string"
},
"paths": {
"description": "Optional. Specific file paths to return contents for (e.g. ['index.html','style.css']). Omit to get all text files. The manifest always lists every file regardless.",
"items": {
"type": "string"
},
"type": "array"
},
"site_id": {
"description": "The site id returned at publish time.",
"type": "string"
}
},
"required": [
"site_id",
"edit_token"
],
"type": "object"
},
"name": "get_site_files",
"outputSchema": {
"properties": {
"files": {
"description": "Inlined contents of the requested text files (default: all text files, capped for size).",
"items": {
"properties": {
"content": {
"description": "Full text content of the file.",
"type": "string"
},
"encoding": {
"description": "Always 'utf-8' \u2014 only text files are inlined.",
"enum": [
"utf-8"
],
"type": "string"
},
"path": {
"description": "Path of this file under the site root.",
"type": "string"
}
},
"required": [
"path",
"content",
"encoding"
],
"type": "object"
},
"type": "array"
},
"manifest": {
"description": "Every file on the site (always complete, regardless of which contents were inlined).",
"items": {
"properties": {
"content_type": {
"description": "Stored content-type, e.g. 'text/html'.",
"type": "string"
},
"is_text": {
"description": "Whether the file is a text type eligible to have its content inlined.",
"type": "boolean"
},
"path": {
"description": "Path under the site root, e.g. 'index.html'.",
"type": "string"
},
"sha256": {
"description": "Hex sha256 of the file bytes; null if not recorded for this file.",
"type": [
"string",
"null"
]
},
"size_bytes": {
"description": "File size in bytes.",
"type": "integer"
}
},
"required": [
"path",
"size_bytes",
"content_type",
"sha256",
"is_text"
],
"type": "object"
},
"type": "array"
},
"site_id": {
"description": "The site's slug / id.",
"type": "string"
},
"truncated": {
"description": "true if some requested file contents were omitted for size \u2014 request specific paths to read them.",
"type": "boolean"
},
"url": {
"description": "The live URL of the site.",
"type": "string"
},
"version": {
"description": "The site's current version \u2014 pass as expected_version to update_site_file to avoid clobbering.",
"type": "integer"
}
},
"required": [
"site_id",
"version",
"url",
"manifest",
"files",
"truncated"
],
"type": "object"
}
},
{
"annotations": {
"destructiveHint": false,
"openWorldHint": true,
"readOnlyHint": false,
"title": "Edit specific files of a published site"
},
"description": "Change one or a few files of an already-published site, leaving every other file untouched (a merge \u2014 unlike deploy, which replaces the whole site). Ideal for small edits: fix a typo in index.html, swap a stylesheet, add one page. Best practice: call get_site_files first, edit the returned content, then call this with the files you changed and the `expected_version` from that read \u2014 if the site changed in the meantime you get a clear conflict telling you to re-read. Requires site_id + edit_token. Cannot delete files (use deploy to drop a file) and cannot remove index.html.",
"inputSchema": {
"properties": {
"edit_token": {
"description": "The edit token returned at publish time.",
"type": "string"
},
"expected_version": {
"description": "Optional but recommended. The `version` you got from get_site_files. If the site has changed since, the update is rejected with a conflict so you can re-read and re-apply. Omit to force last-writer-wins.",
"type": "integer"
},
"files": {
"description": "The files to change. Only these are written; all other files on the site survive.",
"items": {
"properties": {
"content": {
"description": "Full new file body. Text by default; binary must be base64.",
"type": "string"
},
"encoding": {
"description": "Defaults to utf-8 for text, base64 otherwise.",
"enum": [
"base64",
"utf-8"
],
"type": "string"
},
"path": {
"description": "Path under the site root, e.g. 'index.html'.",
"type": "string"
}
},
"required": [
"path",
"content"
],
"type": "object"
},
"minItems": 1,
"type": "array"
},
"site_id": {
"description": "The site id returned at publish time.",
"type": "string"
}
},
"required": [
"site_id",
"edit_token",
"files"
],
"type": "object"
},
"name": "update_site_file",
"outputSchema": {
"properties": {
"files_total": {
"description": "Total number of files on the site after the merge.",
"type": "integer"
},
"files_written": {
"description": "Paths of the files written in this update. All other files were left untouched.",
"items": {
"type": "string"
},
"type": "array"
},
"site_id": {
"description": "The site's slug / id.",
"type": "string"
},
"url": {
"description": "The live URL of the site.",
"type": "string"
},
"version": {
"description": "The site's new version after the merge.",
"type": "integer"
}
},
"required": [
"site_id",
"url",
"version",
"files_written",
"files_total"
],
"type": "object"
}
}
]
}
},
"url": "https://mcp.justpublish.ai/"
},
"latency_ms": 121.5,
"status": "ok"
},
"transport_compliance_probe": {
"details": {
"bad_protocol_error": null,
"bad_protocol_headers": {
"content-type": "text/event-stream",
"mcp-session-id": "8fdf22ade1cdf4d67fdfdb66d1c6f385"
},
"bad_protocol_payload": {
"id": 410,
"jsonrpc": "2.0",
"result": {
"tools": [
{
"_meta": {
"openai/outputTemplate": "ui://just-publish/publish-moment-v1.html",
"openai/toolInvocation/invoked": "Your site is live",
"openai/toolInvocation/invoking": "Publishing your site\u2026",
"openai/widgetCSP": {
"redirect_domains": [
"https://justpublish.site",
"https://justpublish.ai"
]
},
"ui": {
"resourceUri": "ui://just-publish/publish-moment-v1.html"
}
},
"annotations": {
"destructiveHint": false,
"openWorldHint": true,
"readOnlyHint": false,
"title": "Publish a website"
},
"description": "Put a website live at a public URL. Use this when the user wants to publish, launch, or get a page online \u2014 e.g. 'I need a website', 'put up a page for my business', 'make this live'. Takes static files (HTML, CSS, JS, images) and returns a working URL anyone can open. No build step, no config. First call: omit site_id and edit_token \u2014 you get back a url, a site_id, and an edit_token. Keep the edit_token; it's the only way to change this site later. Later calls: pass site_id + edit_token to publish over the same site. deploy REPLACES the whole site \u2014 any file you leave out is DELETED. To change just one or a few files, use update_site_file instead. To see what's currently live before editing, use get_site_files first.",
"inputSchema": {
"properties": {
"edit_token": {
"description": "Edit token returned at create time. Required to update.",
"type": "string"
},
"email": {
"description": "Email to associate with the site. Captured unverified at first deploy; verification only required later for custom domains and recovery.",
"type": "string"
},
"files": {
"description": "Files to publish. Must include an index.html at the root.",
"items": {
"properties": {
"content": {
"description": "File body. Text by default; binary must be base64.",
"type": "string"
},
"encoding": {
"description": "Defaults to utf-8 for text extensions, base64 otherwise.",
"enum": [
"base64",
"utf-8"
],
"type": "string"
},
"path": {
"description": "Path under the site root, e.g. 'index.html', 'assets/logo.png'.",
"type": "string"
}
},
"required": [
"path",
"content"
],
"type": "object"
},
"minItems": 1,
"type": "array"
},
"site_id": {
"description": "Existing site id to update. Omit to create a new site.",
"type": "string"
}
},
"required": [
"files",
"email"
],
"type": "object"
},
"name": "deploy",
"outputSchema": {
"properties": {
"created": {
"description": "true if this call created a new site; false if it updated an existing one.",
"type": "boolean"
},
"dashboard_url": {
"description": "Deep link to this site in the owner's dashboard.",
"type": "string"
},
"edit_token": {
"description": "Returned ONLY on first create. Save it \u2014 it's the only way to update this site.",
"type": "string"
},
"email_masked": {
"description": "The owner email, masked for display (e.g. 'a***@example.com').",
"type": "string"
},
"email_verified": {
"description": "Whether the site's owner email is verified right now. New sites are always false.",
"type": "boolean"
},
"files_uploaded": {
"description": "Number of files written in this deploy.",
"type": "integer"
},
"site_id": {
"description": "The site's slug / id \u2014 pass back to update it later.",
"type": "string"
},
"total_bytes": {
"description": "Total size of the site in bytes after this deploy.",
"type": "integer"
},
"url": {
"description": "The live URL of the published site.",
"type": "string"
},
"verify_required": {
"description": "true when the owner still needs to verify their email (keys on !email_verified).",
"type": "boolean"
}
},
"required": [
"url",
"site_id",
"created",
"email_verified",
"files_uploaded",
"total_bytes",
"email_masked",
"verify_required",
"dashboard_url"
],
"type": "object"
}
},
{
"annotations": {
"destructiveHint": false,
"openWorldHint": false,
"readOnlyHint": true,
"title": "Read a published site's files"
},
"description": "Read the files of a site you already published, so you can make a targeted edit instead of rebuilding the whole site from memory. Returns a complete manifest (every file's path, size, content-type, sha256) plus the contents of the text files (HTML/CSS/JS/etc). Also returns the site's current `version` \u2014 pass it back to update_site_file so you don't overwrite a newer change. Pass `paths` to fetch only specific files; omit it to get all text files. Requires site_id + edit_token.",
"inputSchema": {
"properties": {
"edit_token": {
"description": "The edit token returned at publish time.",
"type": "string"
},
"paths": {
"description": "Optional. Specific file paths to return contents for (e.g. ['index.html','style.css']). Omit to get all text files. The manifest always lists every file regardless.",
"items": {
"type": "string"
},
"type": "array"
},
"site_id": {
"description": "The site id returned at publish time.",
"type": "string"
}
},
"required": [
"site_id",
"edit_token"
],
"type": "object"
},
"name": "get_site_files",
"outputSchema": {
"properties": {
"files": {
"description": "Inlined contents of the requested text files (default: all text files, capped for size).",
"items": {
"properties": {
"content": {
"description": "Full text content of the file.",
"type": "string"
},
"encoding": {
"description": "Always 'utf-8' \u2014 only text files are inlined.",
"enum": [
"utf-8"
],
"type": "string"
},
"path": {
"description": "Path of this file under the site root.",
"type": "string"
}
},
"required": [
"path",
"content",
"encoding"
],
"type": "object"
},
"type": "array"
},
"manifest": {
"description": "Every file on the site (always complete, regardless of which contents were inlined).",
"items": {
"properties": {
"content_type": {
"description": "Stored content-type, e.g. 'text/html'.",
"type": "string"
},
"is_text": {
"description": "Whether the file is a text type eligible to have its content inlined.",
"type": "boolean"
},
"path": {
"description": "Path under the site root, e.g. 'index.html'.",
"type": "string"
},
"sha256": {
"description": "Hex sha256 of the file bytes; null if not recorded for this file.",
"type": [
"string",
"null"
]
},
"size_bytes": {
"description": "File size in bytes.",
"type": "integer"
}
},
"required": [
"path",
"size_bytes",
"content_type",
"sha256",
"is_text"
],
"type": "object"
},
"type": "array"
},
"site_id": {
"description": "The site's slug / id.",
"type": "string"
},
"truncated": {
"description": "true if some requested file contents were omitted for size \u2014 request specific paths to read them.",
"type": "boolean"
},
"url": {
"description": "The live URL of the site.",
"type": "string"
},
"version": {
"description": "The site's current version \u2014 pass as expected_version to update_site_file to avoid clobbering.",
"type": "integer"
}
},
"required": [
"site_id",
"version",
"url",
"manifest",
"files",
"truncated"
],
"type": "object"
}
},
{
"annotations": {
"destructiveHint": false,
"openWorldHint": true,
"readOnlyHint": false,
"title": "Edit specific files of a published site"
},
"description": "Change one or a few files of an already-published site, leaving every other file untouched (a merge \u2014 unlike deploy, which replaces the whole site). Ideal for small edits: fix a typo in index.html, swap a stylesheet, add one page. Best practice: call get_site_files first, edit the returned content, then call this with the files you changed and the `expected_version` from that read \u2014 if the site changed in the meantime you get a clear conflict telling you to re-read. Requires site_id + edit_token. Cannot delete files (use deploy to drop a file) and cannot remove index.html.",
"inputSchema": {
"properties": {
"edit_token": {
"description": "The edit token returned at publish time.",
"type": "string"
},
"expected_version": {
"description": "Optional but recommended. The `version` you got from get_site_files. If the site has changed since, the update is rejected with a conflict so you can re-read and re-apply. Omit to force last-writer-wins.",
"type": "integer"
},
"files": {
"description": "The files to change. Only these are written; all other files on the site survive.",
"items": {
"properties": {
"content": {
"description": "Full new file body. Text by default; binary must be base64.",
"type": "string"
},
"encoding": {
"description": "Defaults to utf-8 for text, base64 otherwise.",
"enum": [
"base64",
"utf-8"
],
"type": "string"
},
"path": {
"description": "Path under the site root, e.g. 'index.html'.",
"type": "string"
}
},
"required": [
"path",
"content"
],
"type": "object"
},
"minItems": 1,
"type": "array"
},
"site_id": {
"description": "The site id returned at publish time.",
"type": "string"
}
},
"required": [
"site_id",
"edit_token",
"files"
],
"type": "object"
},
"name": "update_site_file",
"outputSchema": {
"properties": {
"files_total": {
"description": "Total number of files on the site after the merge.",
"type": "integer"
},
"files_written": {
"description": "Paths of the files written in this update. All other files were left untouched.",
"items": {
"type": "string"
},
"type": "array"
},
"site_id": {
"description": "The site's slug / id.",
"type": "string"
},
"url": {
"description": "The live URL of the site.",
"type": "string"
},
"version": {
"description": "The site's new version after the merge.",
"type": "integer"
}
},
"required": [
"site_id",
"url",
"version",
"files_written",
"files_total"
],
"type": "object"
}
}
]
}
},
"bad_protocol_status_code": 200,
"delete_error": null,
"delete_status_code": 405,
"expired_session_error": null,
"expired_session_status_code": 200,
"issues": [
"missing_protocol_header",
"bad_protocol_not_rejected",
"delete_session_unexpected",
"expired_session_not_404"
],
"last_event_id_visible": false,
"protocol_header_present": false,
"requested_protocol_version": "2025-03-26",
"session_id_present": true,
"transport": "streamable-http"
},
"latency_ms": 48.48,
"status": "error"
},
"utility_coverage_probe": {
"details": {
"completions": {
"advertised": false,
"live_probe": "not_executed",
"sample_target": {
"type": "resource",
"uri": "https://justpublish.ai/.well-known/mcp/overview.md"
}
},
"initialize_capability_keys": [
"resources",
"tools"
],
"pagination": {
"metadata_signal": false,
"next_cursor_methods": [],
"supported": false
},
"tasks": {
"advertised": false,
"http_status": 200,
"probe_status": "missing"
}
},
"latency_ms": 24.24,
"status": "missing"
}
},
"failures": {
"oauth_authorization_server": {
"reason": "no_authorization_server"
},
"oauth_protected_resource": {
"error": "Client error '404 Not Found' for url 'https://mcp.justpublish.ai/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
"url": "https://mcp.justpublish.ai/.well-known/oauth-protected-resource"
},
"openid_configuration": {
"reason": "no_authorization_server"
},
"transport_compliance_probe": {
"bad_protocol_error": null,
"bad_protocol_headers": {
"content-type": "text/event-stream",
"mcp-session-id": "8fdf22ade1cdf4d67fdfdb66d1c6f385"
},
"bad_protocol_payload": {
"id": 410,
"jsonrpc": "2.0",
"result": {
"tools": [
{
"_meta": {
"openai/outputTemplate": "ui://just-publish/publish-moment-v1.html",
"openai/toolInvocation/invoked": "Your site is live",
"openai/toolInvocation/invoking": "Publishing your site\u2026",
"openai/widgetCSP": {
"redirect_domains": [
"https://justpublish.site",
"https://justpublish.ai"
]
},
"ui": {
"resourceUri": "ui://just-publish/publish-moment-v1.html"
}
},
"annotations": {
"destructiveHint": false,
"openWorldHint": true,
"readOnlyHint": false,
"title": "Publish a website"
},
"description": "Put a website live at a public URL. Use this when the user wants to publish, launch, or get a page online \u2014 e.g. 'I need a website', 'put up a page for my business', 'make this live'. Takes static files (HTML, CSS, JS, images) and returns a working URL anyone can open. No build step, no config. First call: omit site_id and edit_token \u2014 you get back a url, a site_id, and an edit_token. Keep the edit_token; it's the only way to change this site later. Later calls: pass site_id + edit_token to publish over the same site. deploy REPLACES the whole site \u2014 any file you leave out is DELETED. To change just one or a few files, use update_site_file instead. To see what's currently live before editing, use get_site_files first.",
"inputSchema": {
"properties": {
"edit_token": {
"description": "Edit token returned at create time. Required to update.",
"type": "string"
},
"email": {
"description": "Email to associate with the site. Captured unverified at first deploy; verification only required later for custom domains and recovery.",
"type": "string"
},
"files": {
"description": "Files to publish. Must include an index.html at the root.",
"items": {
"properties": {
"content": {
"description": "File body. Text by default; binary must be base64.",
"type": "string"
},
"encoding": {
"description": "Defaults to utf-8 for text extensions, base64 otherwise.",
"enum": [
"base64",
"utf-8"
],
"type": "string"
},
"path": {
"description": "Path under the site root, e.g. 'index.html', 'assets/logo.png'.",
"type": "string"
}
},
"required": [
"path",
"content"
],
"type": "object"
},
"minItems": 1,
"type": "array"
},
"site_id": {
"description": "Existing site id to update. Omit to create a new site.",
"type": "string"
}
},
"required": [
"files",
"email"
],
"type": "object"
},
"name": "deploy",
"outputSchema": {
"properties": {
"created": {
"description": "true if this call created a new site; false if it updated an existing one.",
"type": "boolean"
},
"dashboard_url": {
"description": "Deep link to this site in the owner's dashboard.",
"type": "string"
},
"edit_token": {
"description": "Returned ONLY on first create. Save it \u2014 it's the only way to update this site.",
"type": "string"
},
"email_masked": {
"description": "The owner email, masked for display (e.g. 'a***@example.com').",
"type": "string"
},
"email_verified": {
"description": "Whether the site's owner email is verified right now. New sites are always false.",
"type": "boolean"
},
"files_uploaded": {
"description": "Number of files written in this deploy.",
"type": "integer"
},
"site_id": {
"description": "The site's slug / id \u2014 pass back to update it later.",
"type": "string"
},
"total_bytes": {
"description": "Total size of the site in bytes after this deploy.",
"type": "integer"
},
"url": {
"description": "The live URL of the published site.",
"type": "string"
},
"verify_required": {
"description": "true when the owner still needs to verify their email (keys on !email_verified).",
"type": "boolean"
}
},
"required": [
"url",
"site_id",
"created",
"email_verified",
"files_uploaded",
"total_bytes",
"email_masked",
"verify_required",
"dashboard_url"
],
"type": "object"
}
},
{
"annotations": {
"destructiveHint": false,
"openWorldHint": false,
"readOnlyHint": true,
"title": "Read a published site's files"
},
"description": "Read the files of a site you already published, so you can make a targeted edit instead of rebuilding the whole site from memory. Returns a complete manifest (every file's path, size, content-type, sha256) plus the contents of the text files (HTML/CSS/JS/etc). Also returns the site's current `version` \u2014 pass it back to update_site_file so you don't overwrite a newer change. Pass `paths` to fetch only specific files; omit it to get all text files. Requires site_id + edit_token.",
"inputSchema": {
"properties": {
"edit_token": {
"description": "The edit token returned at publish time.",
"type": "string"
},
"paths": {
"description": "Optional. Specific file paths to return contents for (e.g. ['index.html','style.css']). Omit to get all text files. The manifest always lists every file regardless.",
"items": {
"type": "string"
},
"type": "array"
},
"site_id": {
"description": "The site id returned at publish time.",
"type": "string"
}
},
"required": [
"site_id",
"edit_token"
],
"type": "object"
},
"name": "get_site_files",
"outputSchema": {
"properties": {
"files": {
"description": "Inlined contents of the requested text files (default: all text files, capped for size).",
"items": {
"properties": {
"content": {
"description": "Full text content of the file.",
"type": "string"
},
"encoding": {
"description": "Always 'utf-8' \u2014 only text files are inlined.",
"enum": [
"utf-8"
],
"type": "string"
},
"path": {
"description": "Path of this file under the site root.",
"type": "string"
}
},
"required": [
"path",
"content",
"encoding"
],
"type": "object"
},
"type": "array"
},
"manifest": {
"description": "Every file on the site (always complete, regardless of which contents were inlined).",
"items": {
"properties": {
"content_type": {
"description": "Stored content-type, e.g. 'text/html'.",
"type": "string"
},
"is_text": {
"description": "Whether the file is a text type eligible to have its content inlined.",
"type": "boolean"
},
"path": {
"description": "Path under the site root, e.g. 'index.html'.",
"type": "string"
},
"sha256": {
"description": "Hex sha256 of the file bytes; null if not recorded for this file.",
"type": [
"string",
"null"
]
},
"size_bytes": {
"description": "File size in bytes.",
"type": "integer"
}
},
"required": [
"path",
"size_bytes",
"content_type",
"sha256",
"is_text"
],
"type": "object"
},
"type": "array"
},
"site_id": {
"description": "The site's slug / id.",
"type": "string"
},
"truncated": {
"description": "true if some requested file contents were omitted for size \u2014 request specific paths to read them.",
"type": "boolean"
},
"url": {
"description": "The live URL of the site.",
"type": "string"
},
"version": {
"description": "The site's current version \u2014 pass as expected_version to update_site_file to avoid clobbering.",
"type": "integer"
}
},
"required": [
"site_id",
"version",
"url",
"manifest",
"files",
"truncated"
],
"type": "object"
}
},
{
"annotations": {
"destructiveHint": false,
"openWorldHint": true,
"readOnlyHint": false,
"title": "Edit specific files of a published site"
},
"description": "Change one or a few files of an already-published site, leaving every other file untouched (a merge \u2014 unlike deploy, which replaces the whole site). Ideal for small edits: fix a typo in index.html, swap a stylesheet, add one page. Best practice: call get_site_files first, edit the returned content, then call this with the files you changed and the `expected_version` from that read \u2014 if the site changed in the meantime you get a clear conflict telling you to re-read. Requires site_id + edit_token. Cannot delete files (use deploy to drop a file) and cannot remove index.html.",
"inputSchema": {
"properties": {
"edit_token": {
"description": "The edit token returned at publish time.",
"type": "string"
},
"expected_version": {
"description": "Optional but recommended. The `version` you got from get_site_files. If the site has changed since, the update is rejected with a conflict so you can re-read and re-apply. Omit to force last-writer-wins.",
"type": "integer"
},
"files": {
"description": "The files to change. Only these are written; all other files on the site survive.",
"items": {
"properties": {
"content": {
"description": "Full new file body. Text by default; binary must be base64.",
"type": "string"
},
"encoding": {
"description": "Defaults to utf-8 for text, base64 otherwise.",
"enum": [
"base64",
"utf-8"
],
"type": "string"
},
"path": {
"description": "Path under the site root, e.g. 'index.html'.",
"type": "string"
}
},
"required": [
"path",
"content"
],
"type": "object"
},
"minItems": 1,
"type": "array"
},
"site_id": {
"description": "The site id returned at publish time.",
"type": "string"
}
},
"required": [
"site_id",
"edit_token",
"files"
],
"type": "object"
},
"name": "update_site_file",
"outputSchema": {
"properties": {
"files_total": {
"description": "Total number of files on the site after the merge.",
"type": "integer"
},
"files_written": {
"description": "Paths of the files written in this update. All other files were left untouched.",
"items": {
"type": "string"
},
"type": "array"
},
"site_id": {
"description": "The site's slug / id.",
"type": "string"
},
"url": {
"description": "The live URL of the site.",
"type": "string"
},
"version": {
"description": "The site's new version after the merge.",
"type": "integer"
}
},
"required": [
"site_id",
"url",
"version",
"files_written",
"files_total"
],
"type": "object"
}
}
]
}
},
"bad_protocol_status_code": 200,
"delete_error": null,
"delete_status_code": 405,
"expired_session_error": null,
"expired_session_status_code": 200,
"issues": [
"missing_protocol_header",
"bad_protocol_not_rejected",
"delete_session_unexpected",
"expired_session_not_404"
],
"last_event_id_visible": false,
"protocol_header_present": false,
"requested_protocol_version": "2025-03-26",
"session_id_present": true,
"transport": "streamable-http"
}
},
"remote_url": "https://mcp.justpublish.ai/",
"server_card_payload": {
"$schema": "https://static.modelcontextprotocol.io/schemas/v1/server-card.schema.json",
"authentication": {
"required": false
},
"capabilities": {
"prompts": false,
"resources": true,
"tools": true
},
"description": "Publish the website you built with AI to a live public URL \u2014 straight from chat, no setup.",
"icons": [
{
"mimeType": "image/png",
"sizes": [
"512x512"
],
"src": "https://justpublish.ai/icon.png"
},
{
"mimeType": "image/png",
"sizes": [
"192x192"
],
"src": "https://justpublish.ai/icon-192.png"
}
],
"name": "ai.justpublish/just-publish",
"protocolVersion": "2025-11-25",
"remotes": [
{
"supportedProtocolVersions": [
"2025-11-25",
"2025-06-18",
"2025-03-26",
"2024-11-05"
],
"type": "streamable-http",
"url": "https://mcp.justpublish.ai/"
}
],
"repository": {
"source": "github",
"url": "https://github.com/just-done/just-publish-mcp"
},
"serverInfo": {
"description": "Publish the website you built with AI to a live public URL \u2014 straight from chat, no setup.",
"name": "Just Publish",
"version": "0.1.5"
},
"serverUrl": "https://mcp.justpublish.ai/",
"title": "Just Publish",
"tools": [
{
"description": "Put a website live at a public URL from static files (HTML/CSS/JS/images). Returns a working URL, a site_id, and an edit_token. No build step, no login.",
"name": "deploy"
},
{
"description": "Read the files currently live on a site (needs its site_id + edit_token) before editing.",
"name": "get_site_files"
},
{
"description": "Change one or a few files on an existing site in place, without republishing the whole site.",
"name": "update_site_file"
}
],
"transport": {
"endpoint": "https://mcp.justpublish.ai/",
"type": "streamable-http"
},
"version": "0.1.5",
"websiteUrl": "https://justpublish.ai"
},
"server_identifier": "ai.justpublish/just-publish"
}
Known versions
0.1.4
Validation history
7 day score delta
n/a
30 day score delta
n/a
Recent healthy ratio
100%
Freshness
9.9h
| Timestamp | Status | Score | Latency | Tools |
|---|---|---|---|---|
| Aug 09, 2026 07:28:35 AM UTC | Healthy | 65.6 | 1097.9 ms | 3 |
| Aug 08, 2026 07:28:12 PM UTC | Healthy | 39.4 | 1015.2 ms | 0 |
| Aug 08, 2026 07:28:05 AM UTC | Healthy | 39.1 | 994.0 ms | 0 |
| Aug 07, 2026 07:27:30 PM UTC | Healthy | 38.8 | 1155.4 ms | 0 |
| Aug 07, 2026 07:11:19 AM UTC | Healthy | 38.8 | 1007.6 ms | 0 |
| Aug 06, 2026 07:10:59 PM UTC | Healthy | 38.8 | 1131.1 ms | 0 |
| Aug 06, 2026 07:10:32 AM UTC | Healthy | 40.9 | 1120.8 ms | 0 |
| Aug 06, 2026 01:10:27 AM UTC | Healthy | 43.2 | 1311.0 ms | 0 |
Validation timeline
| Validated | Summary | Score | Protocol | Auth mode | Tools | High-risk tools | Changes |
|---|---|---|---|---|---|---|---|
| Aug 09, 2026 07:28:35 AM UTC | Healthy | 65.6 | 2025-03-26 | public | 3 | 2 | auth_mode_changed write_surface_expanded tool_snapshot_changed |
| Aug 08, 2026 07:28:12 PM UTC | Healthy | 39.4 | unknown | unknown | 0 | 0 | none |
| Aug 08, 2026 07:28:05 AM UTC | Healthy | 39.1 | unknown | unknown | 0 | 0 | none |
| Aug 07, 2026 07:27:30 PM UTC | Healthy | 38.8 | unknown | unknown | 0 | 0 | none |
| Aug 07, 2026 07:11:19 AM UTC | Healthy | 38.8 | unknown | unknown | 0 | 0 | none |
| Aug 06, 2026 07:10:59 PM UTC | Healthy | 38.8 | unknown | unknown | 0 | 0 | none |
| Aug 06, 2026 07:10:32 AM UTC | Healthy | 40.9 | unknown | unknown | 0 | 0 | none |
| Aug 06, 2026 01:10:27 AM UTC | Healthy | 43.2 | unknown | unknown | 0 | 0 | none |
| Aug 05, 2026 07:06:43 PM UTC | Healthy | 46.6 | unknown | unknown | 0 | 0 | none |
| Aug 04, 2026 08:51:20 PM UTC | Healthy | 46.2 | unknown | unknown | 0 | 0 | none |
Recent validation runs
| Started | Status | Summary | Latency | Checks |
|---|---|---|---|---|
| Aug 09, 2026 07:28:34 AM UTC | Completed | Healthy | 1097.9 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, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe |
| Aug 08, 2026 07:28:11 PM UTC | Completed | Healthy | 1015.2 ms | |
| Aug 08, 2026 07:28:04 AM UTC | Completed | Healthy | 994.0 ms | |
| Aug 07, 2026 07:27:28 PM UTC | Completed | Healthy | 1155.4 ms | |
| Aug 07, 2026 07:11:18 AM UTC | Completed | Healthy | 1007.6 ms | |
| Aug 06, 2026 07:10:58 PM UTC | Completed | Healthy | 1131.1 ms | |
| Aug 06, 2026 07:10:31 AM UTC | Completed | Healthy | 1120.8 ms | |
| Aug 06, 2026 01:10:26 AM UTC | Completed | Healthy | 1311.0 ms | |
| Aug 05, 2026 07:06:42 PM UTC | Completed | Healthy | 1246.5 ms | |
| Aug 04, 2026 08:51:19 PM UTC | Completed | Healthy | 1106.8 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 09, 2026 07:28:35 AM UTC | Latest validation: healthy | Score 65.6 with status healthy. |
| Aug 09, 2026 07:28:35 AM UTC | Score changed | Score delta +26.2 versus the previous run. |
| Aug 09, 2026 07:28:35 AM UTC | Tool snapshot changed | Added 3, removed 0, and changed 0 tool contracts. |
| Aug 09, 2026 07:28:35 AM UTC | Auth mode changed | Auth mode moved from unknown to public. |
| Aug 08, 2026 07:28:12 PM UTC | Score changed | Score delta +0.3 versus the previous run. |
| Aug 08, 2026 07:28:05 AM UTC | Score changed | Score delta +0.3 versus the previous run. |
| Aug 05, 2026 10:59:55 AM UTC | Score corrected (post-1.0.503 remediation, R1 zero-anchoring) | Prior: 77.01. Corrected: 74.71. |
Capabilities
- OAuth:
- DCR/CIMD:
- Prompts:
- Homepage: https://justpublish.ai
- Docs: none
- Support: none
- Icon: none
- Remote endpoint: https://mcp.justpublish.ai/
- Server card: https://mcp.justpublish.ai/.well-known/mcp/server-card.json
Use-case taxonomy
development search communication web
Benchmark tasks
| Benchmark task | Status | Evidence |
|---|---|---|
| Discover tools | Passes |
|
| Read-only fetch flow | Passes |
|
| OAuth-required connect | Degraded |
|
| Safe write flow with confirmation | Likely to fail |
|
Utility coverage
Probe status
Missing
Completions
not detected
Completion probe target: {
"type": "resource",
"uri": "https://justpublish.ai/.well-known/mcp/overview.md"
}
Pagination
not detected
No nextCursor evidence.
Tasks
Missing
Advertised: no
Transport compliance drilldown
Probe status
Error
Transport
streamable-http
Session header
yes
Protocol header
no
Bad protocol response
200
DELETE teardown
405
Expired session retry
200
Last-Event-ID visible
no
Issues: missing_protocol_header, bad_protocol_not_rejected, delete_session_unexpected, expired_session_not_404
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
deploy get_site_files update_site_file
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
26.24
Summary changed
no
Tool delta
3
Prompt delta
0
Auth mode changed
yes
Write surface expanded
yes
Protocol regressed
no
Registry drift changed
no
Regressed checks: action_safety_probe, oauth_protected_resource, provenance_divergence_probe, transport_compliance_probe
Improved checks: advanced_capabilities_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, official_registry_probe, probe_noise_resilience, prompts_list, resource_read, resources_list, server_card, session_resume_probe, tool_snapshot_probe, tools_list
Newly assessed dimensions: none
No longer assessed dimensions: none
| Component | Previous | Latest | Delta |
|---|---|---|---|
| No component deltas between the latest two runs. | |||
Registry & provenance divergence
Probe status
Not_Assessed
Direct official match
yes
Drift fields
none
| Field | Registry | Live server card |
|---|---|---|
| Title | n/a | Just Publish |
| Version | n/a | 0.1.5 |
| Homepage | n/a | n/a |
Active alerts
- Server card and live tool schemas disagree (medium)
Severity: medium. 3 tool(s) diverge on parameters: deploy, get_site_files, update_site_file. An agent trusting the published card will construct invalid calls. - 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.justpublish/just-publish |
official_registry | yes | 65.6 |
Alias consolidation
Canonical identifier
ai.justpublish/just-publish
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
22/44
Connectivity, auth, and transport expectations for common clients.
Interface Quality
35/56
How well the tool/resource interface communicates and behaves under automation.
Security Posture
22/36
How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.
Reliability & Trust
23/24
Operational stability, consistency, and trustworthiness over time.
Discovery & Governance
18/28
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
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
2/4
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
3/4
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
1/4
Quality of prompt metadata, argument shape, and prompt discoverability for clients.
Resource Contract
4/4
How completely resources and resource templates describe URIs, types, and usage shape.
Discovery Metadata
2/4
Homepage, docs, icon, repository, support, and license coverage for directory consumers.
Registry Consistency
3/4
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
0/4
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
4/4
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
4/4
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
4/4
Whether Streamable HTTP session identifiers and resumed requests behave cleanly for real clients.
Step-Up Auth
0/4
Whether OAuth metadata and WWW-Authenticate challenges support granular, incremental consent instead of broad upfront scopes.
Transport Compliance
1/4
Checks session headers, protocol-version enforcement, session teardown, and expired-session behavior.
Utility Coverage
0/4
Signals support for completions, pagination, and task-oriented utility surfaces that larger clients increasingly expect.
Advanced Capability Coverage
1/4
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
0/4
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
1/4
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.
Safety Transparency
3/4
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
3/4
Penalizes delete/revoke/destroy style tools unless auth and safeguards reduce blast radius.
Egress / SSRF Resilience
1/4
Assesses arbitrary URL fetch, crawl, webhook, and remote-request exposure on the tool surface.
Execution / Sandbox Safety
4/4
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
1/4
Rewards scoped auth metadata and penalizes broad or missing scopes around privileged tools.
Secret Handling Hygiene
1/4
Assesses secret-bearing tools, token leakage risk, and whether the public surface avoids obvious secret exposure.
Supply Chain Signal
2/4
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 | 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 | 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
|
| High | Sync the published server card's tool schemas with the live tool surface | The server card and live tools/list disagree on parameter names, required sets, or types -- clients that trust the published card will construct invalid calls. | Regenerate the published server card from the live tool schemas (or vice versa) so parameter names, required sets, and types match exactly.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 | Respond to server card and live tool schemas disagree | Severity: medium. 3 tool(s) diverge on parameters: deploy, get_site_files, update_site_file. An agent trusting the published card will construct invalid calls. | |
| 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
|
Point loss breakdown
| Component | Current | Points missing |
|---|---|---|
| Utility Coverage | 0/4 | -4.0 |
| Step Up Auth | 0/4 | -4.0 |
| Request Association | 0/4 | -4.0 |
| Recovery Semantics | 0/4 | -4.0 |
| OAUTH Interop | 0/4 | -4.0 |
| Error Contract | 0/4 | -4.0 |
| Transport Compliance | 1/4 | -3.0 |
| Secret Handling Hygiene | 1/4 | -3.0 |
| Prompt Contract | 1/4 | -3.0 |
| Least Privilege Scope | 1/4 | -3.0 |
| Egress SSRF Resilience | 1/4 | -3.0 |
| Advanced Capability Coverage | 1/4 | -3.0 |
Compatibility profiles
OpenAI Connectors
55.6
partial
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance failed or did not complete successfully.; OAuth interoperability should be strong.
Connector URL: https://mcp.justpublish.ai/ # No OAuth metadata detected. # Server: ai.justpublish/just-publish
Claude Desktop
83.3
compatible
Transport behavior should match Claude-compatible HTTP expectations.
{
"mcpServers": {
"just-publish": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.justpublish.ai/"]
}
}
}
Smithery
80.0
compatible
Machine-readable failure semantics should be present.
smithery mcp add "https://mcp.justpublish.ai/"
Generic Streamable HTTP
100.0
compatible
No major blockers detected.
curl -sS https://mcp.justpublish.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): 57.4 • 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
none
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
score_below_hosting_threshold blocked_by_active_alerts blocked_by_production_readiness unsafe_write_action_surface
| 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.justpublish.ai/ # No OAuth metadata detected. # Server: ai.justpublish/just-publish
Claude Desktop
{
"mcpServers": {
"just-publish": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.justpublish.ai/"]
}
}
}
Smithery
smithery mcp add "https://mcp.justpublish.ai/"
Generic Http
curl -sS https://mcp.justpublish.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
deploy get_site_files update_site_file
Observed from the latest live validation against https://mcp.justpublish.ai/. This is the target server surface, not Verify's own inspection tools.
Live capability counts
3 tools • 0 prompts • 5 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.justpublish/just-publish.Direct machine links