Internal reference report / Metadata only

Firecrawl MCP

A dated snapshot of the anonymous MCP endpoint. This report records protocol and catalog evidence, with untested areas shown explicitly.

Anonymous endpoint profile2026-10-15 UTCRunner 1.0.1

JSON evidence Markdown report

What this establishes

The anonymous endpoint advertised three tools and passed four bounded metadata checks. The authenticated profile, tool behavior and real clients were not tested.

All three tools declare read-only behavior. These are server declarations, not verified behavior.

Metadata checks passed: 4
Tool executions: 0
ChatGPT / Claude: Not tested
Overall score: Not assigned

Recorded checks

protocol-negotiation

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

Evidence: request-1

Passed

initialized-notification

The initialization notification received HTTP 202 with an empty body.

Evidence: request-2

Passed

tool-catalog

Observed the complete advertised catalog: 3 tools across 1 pages.

Evidence: request-3

Passed

tool-metadata-shape

SDK metadata shape checked for 3 observed tools. This is not complete JSON Schema validation or behavior verification.

Evidence: request-3

Passed

oauth-login

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

Not tested

Observed tool catalog

Tool names were observed through tools/list. None of these tools was executed.

firecrawl_parse
firecrawl_scrape
firecrawl_search

Endpoint and provenance

Endpoint: https://mcp.firecrawl.dev/v2/mcp
Profile: Anonymous, keyless endpoint
Protocol: 2025-11-25
Observed at: 2026-10-15T02:06:06.188Z
Run ID: 2bbc87d5-bf46-4869-82e0-5e17c4254302
SHA-256: c2bcfa49be792c8776fff4bb7c003e8b85e4bad933528dfe2edd07f322129198

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.

JSON evidence Markdown report

What this report does not establish

OAuth, authenticated execution, full JSON Schema semantics, security, task success, ChatGPT, Claude and official publication approval were not verified.

Metadata-only internal unpaid reference run. 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 two exact owner-approved HTTPS URLs 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.

Have an MCP endpoint worth reviewing?

Email a public endpoint or repository, the client you care about and one task you need to work. We will discuss scope and sandbox access before any testing.

Discuss a review

Opens your email app. Do not send keys, tokens or private customer data. This is a scope request, not an automatic scan or purchase.