Firecrawl MCP Server
A Model Context Protocol (MCP) server that brings Firecrawl to MCP-compatible AI agents - search, scrape, and interact with the live web for clean, agent-ready context. Its 11 documented tools cover firecrawl, monitor, research, papers. It runs locally over stdio via the published package.
People who work with firecrawl, monitor and research and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.
VERIFIED ACTIVE
LAST COMMIT 2026-09-18 · ★ 7,478 · #1 OF 93 MAINTAINED WEB SCRAPING · VERIFIED 2026-09-18
MIT · TypeScript servers · how we verify → /methodology
01 · Install Firecrawl MCP Server
before you install - you'll need
Set FIRECRAWL_API_KEY before connecting. FIRECRAWL_API_URL is optional or environment-specific per the README.
Claude Code
claude mcp add firecrawl-firecrawl-mcp-server -- npx -y firecrawl-mcp Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"firecrawl-firecrawl-mcp-server": {
"command": "npx",
"args": [
"-y",
"firecrawl-mcp"
]
}
}
} Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.
Using another client? Same JSON, different key
Claude Desktop · mcpServers
Cursor · mcpServers
VS Code · servers
Windsurf · mcpServers
Zed · context_servers
Cline · mcpServers
Roo Code · mcpServers
Continue · mcpServers
LibreChat · mcpServers
Gemini CLI · mcpServers
Codex CLI · mcp_servers
Full setup guides: every client.
02 · Evidence
Security posture
What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.
runs as local process (stdio) - runs on your machine with your user's permissions
license MIT - declared in the repository
npm package firecrawl-mcp - unscoped; check the name against the project README before installing
registry namespace io.github.firecrawl is GitHub-verified and matches the repo owner
03 · What Firecrawl MCP Server can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
What you can build
With this server connected, an agent can search paper metadata and abstracts with a natural-language query, with optional author, category, and date filters, retrieve canonical metadata for one paper ID (arXiv, PMC, PMID, or DOI), read full-text passages from a specific paper, and list monitors.
The 11 tools it gives your agent
Extracted from the project's README - what Firecrawl MCP Server lets an agent do.
- firecrawl_research_search_papers
- - search paper metadata and abstracts with a natural-language query, with optional author, category, and date filters.
- firecrawl_research_inspect_paper
- - retrieve canonical metadata for one paper ID (arXiv, PMC, PMID, or DOI).
- firecrawl_research_related_papers
- - expand from one or more anchor papers through the citation graph.
- firecrawl_research_read_paper
- - read full-text passages from a specific paper.
- firecrawl_monitor_list
- - list monitors.
- firecrawl_monitor_get
- - get one monitor.
- firecrawl_monitor_update
- - update fields including goal, judgeEnabled, webhook, and notification.
- firecrawl_monitor_run
- - trigger a check now.
- firecrawl_monitor_delete
- - delete a monitor (destructive; only call when the user intends to remove it).
- firecrawl_monitor_checks
- - list checks, optionally filtered by status.
- firecrawl_monitor_check
- - get page-level results, including diff, snapshot, judgment.meaningful, and judgment.meaningfulChanges.
Latest releases
v3.2.1 · 2025-09-26
Adjusted search to include query operators in the prompt
v3.2.0 · 2025-09-16
Fixed an issue where self host instances where requiring an API_KEY even if a custom base url was set.
v3.0.0 · 2025-09-11
(feat/versioning) Support for v1 and v2 · wrap safeLogs outside of try-catch and name anon functions for better debugging · Fastmcp · New Contributors · @mogery made their first contribution in
In the wild · how people use Firecrawl MCP Server
Public posts that name a concrete use case. Linked source posts - not MCPhq reviews, ratings, or endorsements.
-
@firecrawl · · Official scrape tools in Cursor/Claude
“Introducing the Official Firecrawl MCP Server - Give web scraping abilities to Cursor, Claude Desktop and more.”
-
@firecrawl · · PDF/spreadsheet parse for agents
“We're launching 5x faster document parsing in the Firecrawl MCP. Use /parse to turn PDFs, spreadsheets, and docs into LLM-ready data for your agents.”
-
@_avichawla · · Scrape inside Cursor/Claude
“Firecrawl MCP server - This adds powerful web scraping capabilities to Cursor, Claude, and any other LLM clients using @firecrawl.”
04 · Who maintains Firecrawl MCP Server
Firecrawl MCP Server is maintained by firecrawl. It's the only MCP server we track from this author; the repo dates to Dec 2024.
05 · Facts
- repository
- github.com/firecrawl/firecrawl-mcp-server
- category
- web scraping - ranked #1 of 93 actively-maintained web scraping servers as of 2026-09-18.
- registry
- io.github.firecrawl/firecrawl-mcp-server (active, first published 2025-10-19 · 21 versions)
- packages
- npm:firecrawl-mcp
06 · Firecrawl MCP Server FAQ
Is Firecrawl MCP Server still maintained?
Yes - as of 2026-09-18, its last commit was 2026-09-18. We re-verify nightly.
What can Firecrawl MCP Server do?
With this server connected, an agent can search paper metadata and abstracts with a natural-language query, with optional author, category, and date filters, retrieve canonical metadata for one paper ID (arXiv, PMC, PMID, or DOI), read full-text passages from a specific paper, and list monitors.
How do I install Firecrawl MCP Server?
Run `npx -y firecrawl-mcp`. The README documents 2 environment variables (FIRECRAWL_API_KEY, FIRECRAWL_API_URL) to set first. Set FIRECRAWL_API_KEY before connecting. FIRECRAWL_API_URL is optional or environment-specific per the README. You can also paste the ready-made client config above.
Does Firecrawl MCP Server run locally?
Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.
07 · Alternatives to Firecrawl MCP Server
Alternatives to Firecrawl MCP Server
Maintained web scraping servers if Firecrawl MCP Server isn't the fit.
- Apify MCP Server Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡ ★ 7,456 · 2026-09-17
- Wigolo Local-first web intelligence MCP server for AI coding agents ★ 5,284 · 2026-09-17
- Exa Fast, intelligent web search and web crawling. New mcp tool: Exa-code is a context tool for coding ★ 5,013 · 2026-08-21
- Tavily MCP MCP server for advanced web search using Tavily ★ 2,390 · 2026-09-16
- Open Brand Extract brand assets (logos, colors, backdrop images, brand name) from any website URL ★ 797 · 2026-05-12
- Omnisearch MCP server for integrating Omnisearch with LLMs ★ 349 · 2026-09-18
Pairs well with
Servers that cover what Firecrawl MCP Server doesn't - only shown when the pairing reason fits the companion.
- SearXNG Search → search companion search · ★ 1,245
- Blockrun MCP → search companion search · ★ 394
- Supabase → database companion database · ★ 2,910
- MongoDB MCP Server → database companion database · ★ 1,131
- Codebase Memory → memory companion memory · ★ 43,715
- Memorix → memory companion memory · ★ 785
head to head · Firecrawl MCP Server vs Tavily MCP · Firecrawl MCP Server vs Wigolo
More web scraping MCP servers · Fouradata MCP Server · Glim Sh · Gmapsscraper MCP Server · GoAnyAPI MCP · CN Scraper MCP
More TypeScript MCP servers · Dyslex Ia · Flight505 MCP Dincoder · Fr24api MCP · Fatsecret MCP · Qrcodly · see all