Skills/npm/firecrawl-mcp

firecrawl-mcp@3.41.0

VERIFIED

Publisher 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.

Registry npm (MCP server)Publisher firecrawl · publishing for 636 daysInstalls 663KLast detonated 1 h ago
$claude mcp add firecrawl-mcp -- npx -y firecrawl-mcp
WatchReport an issue

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.

$vet-skills run --secrets FIRECRAWL_API_KEY=firecrawl.dev,FIRECRAWL_MCP_SEARCH_OAUTH_ONLY=firecrawl.dev,FIRECRAWL_OAUTH_INTROSPECT_CACHE_TTL_MS=firecrawl.dev,FIRECRAWL_OAUTH_INTROSPECT_SECRET=firecrawl.dev,FIRECRAWL_OAUTH_ISSUER=firecrawl.dev,FIRECRAWL_OAUTH_TOKEN=firecrawl.dev,MCP_DELEGATED_CREDENTIAL_SECRET=firecrawl.dev,MCP_OAUTH_ACCEPT_LEGACY_V2_MCP_AUD=firecrawl.dev -- npx -y firecrawl-mcp

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 3.41.0

This 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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
11sprocessdependency install exit 0
31sclaimed28 tools: firecrawl_scrape, firecrawl_map, firecrawl_search, alexandria_library_search, alexandria_library_read, firecrawl_crawl, firecrawl_check_crawl_status, firecrawl_agent, firecrawl_agent_status, firecrawl_interact, firecrawl_interact_stop, firecrawl_parse, firecrawl_monitor_create, firecrawl_monitor_list, firecrawl_monitor_get, firecrawl_monitor_update, firecrawl_monitor_delete, firecrawl_monitor_run, firecrawl_monitor_checks, firecrawl_monitor_check, firecrawl_research_search_papers, firecrawl_research_inspect_paper, firecrawl_research_related_papers, firecrawl_research_read_paper, firecrawl_research_lookup_protein
31stools2adbefa14b2db5d9
31stoolsa455d41060121703
31stools9864147cbd391e4e
31stools499b574c21c2d7e7
31stoolsb93b2be4e7c80890
31stools3971b947be55e883
31stoolsb0e364154daf0e93
31stoolsb8fbbc7b3f3208c2
31stools01df9df43e49a20d
31stoolsa323e9189d172869
31stools0bf5bbce9995f386
31stoolsbf0f1a4e54056704
31stoolsb557c764176a209e
31stoolse6673eb3d310981d
31stoolsa06f332c6b936a73
31stoolsd024e8abc84a8c34
31stools4f7d5b3554545505
31stoolsd2d59fb2f14a8268
31stools3f805ce06b6d81f6
31stools6f0318cb76403a9c
31stools5a19ec2097baa838
31stools923e9910fca26fab
31stools54de2f0168376207
31stoolsda56ec453b26e887
31stools2af6caf8bf4c8547
31stools5ae8ae38037b6428
31stools285b96ee9f341bf1
31stoolsf655a07144d0e2c8
31sprocessscript backend runs setup only
31sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actiondist/server.js:2400 · File type combined with upload action — agent may exfiltrate local data files… 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.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)dist/server.d.ts:706 · MCP server using network transport (SSE/HTTP) — data sent over network…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.
AST04
MEDIUM
File type combined with upload actiondist/index.js:2398 · File type combined with upload action — agent may exfiltrate local data files… 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.
AST07

Cost to the agent

Instructions loaded
≈101 tok
1 file · 13 in bundle
Tool list per prompt
≈13,937 tok
28 tools · 498 per tool
Handshake
2626 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 743

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.