firecrawl-mcp@3.41.0
VERIFIEDPublisher claims: "Firecrawl MCP server, the context API for AI agents: search, scrape, parse, crawl, map, and interact with the web, run Agent and Monitor jobs, and search scientific papers (PubMed, bioRxiv, medRxiv, arXiv). Works with Firecrawl cloud or a self-hosted inst" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Server started and answered tools/list.- Tested
- MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
- Not tested
- what the tools do when called with real credentials
Before you give it your token
- It will ask for
FIRECRAWL_API_KEYFIRECRAWL_MCP_SEARCH_OAUTH_ONLYFIRECRAWL_OAUTH_INTROSPECT_CACHE_TTL_MSFIRECRAWL_OAUTH_INTROSPECT_SECRETFIRECRAWL_OAUTH_ISSUERFIRECRAWL_OAUTH_TOKENMCP_DELEGATED_CREDENTIAL_SECRETMCP_OAUTH_ACCEPT_LEGACY_V2_MCP_AUDConfiguration, not credentials: CLOUD_SERVICE, FASTMCP_ENDPOINT, FASTMCP_HOST, FASTMCP_PORT, FASTMCP_STATELESS, FIRECRAWL_API_URL, FIRECRAWL_INTEGRATION, FIRECRAWL_MCP_ALLOWED_HOSTS, FIRECRAWL_MCP_LIBRARY_SKILLS, FIRECRAWL_MCP_RESOURCE_URL, FIRECRAWL_MCP_SEARCH_ENABLED, FIRECRAWL_MCP_SEARCH_ENDPOINT, FIRECRAWL_MCP_SEARCH_PORT, FIRECRAWL_MCP_SEARCH_RESOURCE_URL, HTTP_STREAMABLE_SERVER, JOB_PATH, SSE_LOCAL- Where it talks to
- firecrawl.dev (its own)Also greenhouse.io — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- what the tools do when called with real credentials
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names greenhouse.io as well as its own vendor. The guard injects FIRECRAWL_API_KEY, FIRECRAWL_MCP_SEARCH_OAUTH_ONLY, FIRECRAWL_OAUTH_INTROSPECT_CACHE_TTL_MS, FIRECRAWL_OAUTH_INTROSPECT_SECRET, FIRECRAWL_OAUTH_ISSUER, FIRECRAWL_OAUTH_TOKEN, MCP_DELEGATED_CREDENTIAL_SECRET, MCP_OAUTH_ACCEPT_LEGACY_V2_MCP_AUD only into requests to firecrawl.dev (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 3.40.0
vet-skills diff firecrawl-mcp 3.40.0 3.41.0This version reaches for something 3.40.0 did not: 1 new host (greenhouse.io). Compared from the two recorded runs, not from source.
- New hosts
- greenhouse.io
Only one of the two runs produced a tool list; tools are not compared.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-19 and scored it 91/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 31 s · 2 scenarios · 0 deviationsStatic findings
… full result. To read the rest, follow nextTool: it runs a command over response.json, where call i's data is .data.alexandria[i].data, in a virtual Bash; then reuse workspaceId with your own command. Send each Bash call alone. The shell h…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.…LARED_ORIGIN_HEADER, type DeferredResult, type ExtraToolsContext, type FirecrawlMcpServer, type FirecrawlMcpServerHooks, type FirecrawlMcpServerOptions, type FirecrawlMcpServerStartArgs, type HttpApp, type InstructionDefaults, keylessToolN…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.… full result. To read the rest, follow nextTool: it runs a command over response.json, where call i's data is .data.alexandria[i].data, in a virtual Bash; then reuse workspaceId with your own command. Send each Bash call alone. The shell h…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.