Firecrawl Official Remote MCP Server
Firecrawl's hosted MCP (mcp.firecrawl.dev/v2/mcp) exposes the full v2 scraping toolkit โ scrape, map, crawl, search and structured extract โ behind a Bearer API key.
- Provider
- Firecrawl โ
- Source
- https://github.com/firecrawl/firecrawl-mcp-server โ
- Categories
- ๐ Documentation, Search & Context๐ ๏ธ Developer Tools & Git
ไธญๆ็ฎไป
Firecrawl ๅฎๆน่ฟ็จ MCP ๆๅกๅจใAI ไปฃ็ๅฏๅฐ้กต้ขๆๅไธบ Markdownใๆ ๅฐ็ซ็น็ปๆใๆด็ซๆๅๅนถๆๅ็ปๆๅๆฐๆฎ๏ผBearer API Key๏ผtools/list ๆฏๆๅฟๅๆกๆ๏ผใ
Maintainer of Firecrawl Web Scraper? Claim or update this listing โ
๐ Client-side only โ never leaves your browser.
Or add to ~/.cursor/mcp.json:
{
"mcpServers": {
"firecrawl": {
"url": "https://mcp.firecrawl.dev/v2/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}claude mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcp
With credential header:
claude mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcp --header "Authorization: Bearer YOUR_API_KEY"
Or add to .vscode/mcp.json:
{
"servers": {
"firecrawl": {
"type": "http",
"url": "https://mcp.firecrawl.dev/v2/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}- Open Settings โ Connectors (Integrations) โ Add Custom Connector.
- Paste the endpoint URL:
https://mcp.firecrawl.dev/v2/mcp - Provide your API key / Bearer token when prompted.
Bridge the remote endpoint into stdio with mcp-remote in claude_desktop_config.json:
{
"mcpServers": {
"firecrawl": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.firecrawl.dev/v2/mcp",
"--header",
"Authorization: Bearer YOUR_API_KEY"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"firecrawl": {
"serverUrl": "https://mcp.firecrawl.dev/v2/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Add to ~/.kiro/settings/mcp.json (or .kiro/settings/mcp.json in your workspace), then reopen Kiro's Agent panel to pick up the server:
{
"mcpServers": {
"firecrawl": {
"url": "https://mcp.firecrawl.dev/v2/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Add to ~/.codex/config.toml โ Codex reads remote HTTP servers from [mcp_servers.*] tables:
[mcp_servers.firecrawl] url = "https://mcp.firecrawl.dev/v2/mcp" bearer_token_env_var = "FIRECRAWL_TOKEN"
Add to cline_mcp_settings.json (Cline โ MCP Servers โ Configure), or paste it via Cline's MCP marketplace file:
{
"mcpServers": {
"firecrawl": {
"type": "streamableHttp",
"url": "https://mcp.firecrawl.dev/v2/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Add to ~/.gemini/settings.json under mcpServers โ httpUrl for Streamable HTTP, url for legacy SSE:
{
"mcpServers": {
"firecrawl": {
"httpUrl": "https://mcp.firecrawl.dev/v2/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}๐งฐ Firecrawl Web Scraper MCP Tools & Schema (10)
| Tool | Safety | Description | Parameters |
|---|---|---|---|
| firecrawl_scrape ~32 tok | ๐ข Read | Scrape a URL into clean markdown. | โ |
| firecrawl_map ~30 tok | ๐ข Read | Map a website's URL structure. | โ |
| firecrawl_crawl ~32 tok | ๐ Write | Start an async crawl of a website. | โ |
| firecrawl_check_crawl_status ~33 tok | ๐ข Read | Check status of a crawl job. | โ |
| firecrawl_search ~32 tok | ๐ข Read | Search the web and scrape results. | โ |
| firecrawl_extract ~32 tok | ๐ข Read | Extract structured data from URLs. | โ |
| firecrawl_deep_research ~33 tok | ๐ Write | Run deep research across the web. | โ |
| firecrawl_generate_llmstxt ~33 tok | ๐ข Read | Generate llms.txt for a site. | โ |
| firecrawl_batch_scrape ~32 tok | ๐ข Read | Batch-scrape multiple URLs. | โ |
| firecrawl_extract_status ~33 tok | ๐ข Read | Get status of an extract job. | โ |
๐ก๏ธ Security, Quality & Context Token Audit
Every tool definition (name + description + input schema) is injected into your LLMโs context on every request โ Estimate per-call LLM token cost โ
- No prompt-injection or hidden-character anomalies detected in tool descriptions
- Streamable HTTP primary endpoint (current 2025-03-26 transport)
- Static credential (Bearer token / API key) โ protect it in client config
- Official first-party endpoint operated by the vendor
- Manually verified by RemoteMCP.net
๐ OAuth 2.1 & Security
- Auth type
- Bearer Token
- Dynamic Client Registration
- โ
- PKCE S256
- โ
- Protected resource metadata
- https://mcp.firecrawl.dev/.well-known/oauth-protected-resource (expected location)
๐งฉ Recommended Agent Skills
๐ Firecrawl Web Scraper MCP Endpoint Overview & Security Guide
Firecrawl Web Scraper MCP โ Remote MCP Server
Firecrawl's remote MCP is the standard agent-scraping endpoint: single-page scrape to clean markdown, site mapping, multi-page crawl jobs, LLM extraction to a schema and built-in search โ keyed by a Firecrawl API key sent as a Bearer token.
Official Firecrawl Web Scraper MCP Endpoint & Transport Architecture
- Endpoint URL:
https://mcp.firecrawl.dev/v2/mcp - Transport: Streamable HTTP
Streamable HTTP is the current MCP transport (2025-03-26 spec): a single URL accepts JSON-RPC POSTs and may stream responses over SSE, so one endpoint serves both simple and streaming workloads. Firecrawl Web Scraper MCP does not publish a separate legacy SSE endpoint, so your client must speak Streamable HTTP.
Authentication, Scopes & Permission Boundaries
Firecrawl Web Scraper MCP uses bearer-token authentication. Create an access token in your Firecrawl account settings, then send it as Authorization: Bearer <token>. No OAuth redirect flow is involved.
Of the 6 cataloged tools, 5 are read-only and 1 can write or mutate state (create resources, run SQL, post messages). Grant access only to the accounts and projects you intend agents to act on, and prefer scoped credentials or a dedicated workspace where the provider supports them.
Common Troubleshooting & Connection Tips
- 401/403 responses โ your credential is missing or rejected. Regenerate the key/token and make sure it is sent as an
Authorization: Bearerheader on every request, including theinitializecall. - "Session expired" / stale
Mcp-Session-Idโ just re-sendinitialize; stateless clients can ignore session headers entirely. - tools/list responds to anonymous handshakes โ you can inspect the tool surface before keying in credentials.
- Crawl jobs are async โ use the status tool to poll completion.
๐ How to Connect
- Copy the Firecrawl Web Scraper MCP endpoint URLThe remote endpoint is https://mcp.firecrawl.dev/v2/mcp.
- Add it to your MCP clientClaude Code:
claude mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcp. Cursor: add"firecrawl": { "url": "https://mcp.firecrawl.dev/v2/mcp" }undermcpServersin ~/.cursor/mcp.json. Other clients work similarly. - Configure your credentialGenerate an access token at https://docs.firecrawl.dev/ and add an
Authorization: Bearer <token>header to the server's config (supported by Cursor, VS Code, Windsurf and mcp-remote --header). - Verify with the online inspectorPaste https://mcp.firecrawl.dev/v2/mcp into remotemcp.net/inspector, run initialize and tools/list, and confirm Firecrawl Web Scraper MCP's 6 tools respond.
โ FAQ
What is the Firecrawl Web Scraper MCP remote MCP endpoint?
The primary endpoint is https://mcp.firecrawl.dev/v2/mcp. It is an official first-party server operated by Firecrawl, speaking the Streamable HTTP transport.
How do I authenticate with Firecrawl Web Scraper MCP?
Firecrawl Web Scraper MCP expects a credential sent as an Authorization: Bearer header. Generate the token in your Firecrawl account and add it to your client's headers.
I'm getting a 401 Unauthorized from Firecrawl Web Scraper MCP โ what's wrong?
Your Bearer credential is missing, malformed or expired. Confirm it is attached to every request โ including initialize โ and that no proxy is stripping the Authorization header.
Which MCP clients work with Firecrawl Web Scraper MCP?
Any client that supports remote MCP servers: Cursor, Claude Code (`claude mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcp`), VS Code Copilot, ChatGPT connectors, Windsurf, Kiro (`~/.kiro/settings/mcp.json`), and Claude Desktop via the `mcp-remote` bridge.
What tools does Firecrawl Web Scraper MCP expose?
6 tools are cataloged in this directory โ including `firecrawl_scrape`, `firecrawl_search`, `firecrawl_map` and more. Use our online inspector to fetch the live tool list straight from the endpoint.
๐ Connect Guides
โ๏ธ Featured in Comparisons
๐ Embed Status Badge in README
Related Servers
AWS Knowledge's hosted remote MCP server. AWS's fully-managed public knowledge MCP gives agents access to the latest AWS documentation, API references, What's New posts and architectural guidance across all AWS services. It is public and unauthenticated โ connect and call tools immediately.
Claude Skills's hosted remote MCP server. ClaudeSkills.club's public MCP lets agents search and pull from a catalog of 90,000+ Agent Skills (SKILL.md) โ workflow specs, safety scores and one-line install instructions. It is public and unauthenticated โ connect and call tools immediately.
Cloudflare's free, authless documentation MCP server. Agents can search the full Cloudflare docs corpus โ no account or token required.
Microsoft Learn's hosted remote MCP server. Microsoft's official Learn MCP server streams trusted, up-to-date documentation for Azure, .NET, Microsoft 365 and the full Microsoft technical catalog directly into agent context. It is public and unauthenticated โ connect and call tools immediately.