All public server reports

Endpoint report / Metadata only

OpenAI Developer Docs MCP

A dated endpoint inspection. Metadata and any separately recorded tool call have their own evidence, scope and limitations.

Developer documentationRunner 1.1.0

What this establishes

The anonymous endpoint advertised 5 tools and passed four bounded metadata checks. Tool execution was not tested. Actual ChatGPT and Claude workflows were not tested.

Tool names and metadata are server declarations. Advertised capabilities are not evidence of successful task execution.

Connection and metadata
Metadata checks passed
Observed tool catalog
Complete: 5 tools
Read-only smoke test
Not tested
ChatGPT / Claude
Not tested / Not tested
Overall score
Not assigned

Recorded checks

These checks cover the metadata inspection. They are separate from the tool-call result above, when present.

protocol-negotiation

Negotiated protocol 2025-11-25; this does not establish host compatibility.

Passed

initialized-notification

The initialization notification received HTTP 202 with an empty body.

Passed

tool-catalog

Observed the complete advertised catalog: 5 tools across 1 pages.

Passed

tool-metadata-shape

SDK metadata shape checked for 5 observed tools. This is not complete JSON Schema validation or behavior verification.

Passed

oauth-login

OAuth discovery, login, token refresh and authenticated access are outside this anonymous inspection.

Not tested

Metadata request evidence

request-1 / initialize

2026-10-15T07:14:22.147Z

HTTP 200 · 956 ms · 193 B

response-received

request-2 / notifications/initialized

2026-10-15T07:14:23.103Z

HTTP 202 · 176 ms · 0 B

notification-accepted

request-3 / tools/list

2026-10-15T07:14:23.279Z

HTTP 200 · 178 ms · 3311 B

response-received

Observed tool catalog

Names were advertised through tools/list. Any tool execution is recorded separately in the smoke test section.

Complete: 5 tools
  • fetch_openai_doc
  • get_openapi_spec
  • list_api_endpoints
  • list_openai_docs
  • search_openai_docs

Endpoint and provenance

Endpoint
https://developers.openai.com/mcp
Official source
https://developers.openai.com/learn/docs-mcp
Profile
Anonymous endpoint profile
Requested protocol
2025-11-25
Reported protocol
2025-11-25
Protocol
2025-11-25
Observed at
2026-10-15T07:14:23.457Z
Run ID
a4e8181f-679c-4023-917f-11ee2482fee4
Catalog SHA-256
5ad0dafb4c06251c121eee0ad28ef8b90349d555f66cfdba92d9b372359bef24
Fingerprint scope
complete-catalog

SHA-256 of all observed tool objects, recursively sorted object keys and sorted canonical tool strings; schema array order is preserved. Raw descriptions, schemas and headers are not persisted.

Inspection bounds
requestTimeoutMs
5,000
runTimeoutMs
30,000
responseBytes
1,048,576
requests
7
pages
5
tools
200
Read the full methodology (English Markdown)

What this report does not establish

These observations do not establish general task success, security, OAuth behavior or ChatGPT and Claude compatibility. Read the limits of each recorded test.

  • Metadata-only anonymous inspection. No tools/call, OAuth flow, API model calls, host UI or publication review was executed. No global quality or safety score is produced.
  • Annotations are server declarations, not verified behavior. Metadata success does not establish task success, security, usefulness or ChatGPT/Claude compatibility.
  • Only active exact HTTPS endpoints in the reviewed source registry are accepted. Redirects, supplied credentials, arbitrary endpoints and OAuth URL fetching are disabled. DNS/TLS use the local runtime: this is not a hardened multi-tenant SSRF sandbox and must not be exposed as a public scanner.
  • Session identifiers are used only in memory. Request/response headers, raw error messages, raw descriptions and schemas are excluded from artifacts. Tool names and aggregate metadata remain untrusted server input.
  • Only the recorded protocol versions and bounded catalog prefix are supported. Reaching a bound or lacking access means unknown, not a failed server or a passing full audit.

What should your MCP do better?

Share a public endpoint or repository, the tasks that matter, and the clients your users use. We will discuss a pilot scope, access and price.

Discuss a benchmark

Opens your email app. Send public links only; arrange sandbox access separately.

Was this helpful?

Anonymous feedback helps us improve pages and translations.