Directory / Search & discovery
Firecrawl
Web search, page scraping to Markdown or JSON, PDF and document parsing, site crawl and map, and browser interaction for AI agents. Without an API key the hosted endpoint offers search, scrape and parse on a rate-limited free tier; the other tools need an API key or OAuth. Endpoint: https://mcp.firecrawl.dev/v2/mcp · Install: npx -y firecrawl-mcp · Docs · Registry: io.github.firecrawl/firecrawl-mcp-server
Live Answered an MCP handshake without credentials and listed 3 tools.
- Category
- Search & discovery
- Transport
http- Source
- https://github.com/firecrawl/firecrawl-mcp-server
- Endpoint
https://mcp.firecrawl.dev/v2/mcp- MCP Registry
io.github.firecrawl/firecrawl-mcp-server- Reports itself as
- firecrawl-fastmcp 3.41.0
- Protocol
- 2025-06-18
- Tools
- 3
- Context cost
- about 4,308 tokens for the tool definitions (estimated at four characters per token)
- Tool definitions last changed
- 2026-11-22
- Handshake time
- 139 ms
- Repository
- 7,881 stars · last push 2026-11-22 · MIT
- Last checked
- 2026-11-22 11:27:33 UTC
- Listed since
- 2026-11-18
Health and compatibility
| Endpoint reachable | Verified | Responded in 139 ms |
|---|---|---|
| MCP handshake (initialize) | Verified | Completed without credentials |
| Tool discovery (tools/list) | Verified | 3 tools listed |
| Authentication | Verified | None needed to connect |
| Protocol version | Verified | 2025-06-18 |
| Transport | Verified | Streamable HTTP |
| Capabilities declared | Verified | completions, logging, resources, tools |
Last checked . Verified means the check saw it happen; it says nothing about whether the server is safe.
Recent history
5 daily checks so far; median response 139 ms. Green answered, violet asked for auth, red did not answer.
Set up in your client
Claude Code
Run this in a terminal:
claude mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcpClaude Desktop
Open Settings → Connectors → Add custom connector and paste this URL:
https://mcp.firecrawl.dev/v2/mcpOr bridge it through mcp-remote in claude_desktop_config.json (needs Node.js):
{
"mcpServers": {
"firecrawl": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.firecrawl.dev/v2/mcp"
]
}
}
}Cursor
Or add it to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):
{
"mcpServers": {
"firecrawl": {
"url": "https://mcp.firecrawl.dev/v2/mcp"
}
}
}VS Code
Or add it to .vscode/mcp.json:
{
"servers": {
"firecrawl": {
"type": "http",
"url": "https://mcp.firecrawl.dev/v2/mcp"
}
}
}Or from a terminal:
code --add-mcp '{"name": "firecrawl", "type": "http", "url": "https://mcp.firecrawl.dev/v2/mcp"}'Windsurf
Add it to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"firecrawl": {
"serverUrl": "https://mcp.firecrawl.dev/v2/mcp"
}
}
}Other clients
Most clients accept this shape. The endpoint is:
https://mcp.firecrawl.dev/v2/mcp{
"mcpServers": {
"firecrawl": {
"type": "http",
"url": "https://mcp.firecrawl.dev/v2/mcp"
}
}
}If it does not connect
- Restart the client after editing a config file, and keep keys out of files you commit.
- If the tools do not appear, open the client's MCP log: a 401 means the credentials were not accepted, and a timeout means the server did not answer.
Tools 3
Names, descriptions and input schemas exactly as the server returned them on 2026-11-22. This is the server author's own text. Nothing is run from this page. Labels such as read-only are declared by the server and are not verified. Raw JSON
firecrawl_parseread-onlyParse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a …
Parse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema. Supported inputs include common HTML, PDF, Word, RTF, OpenDocument, and spreadsheet files; PDF parsing can be bounded with `pdfOptions.maxPages`. Local MCP reads `filePath` from the server filesystem. Hosted MCP uses two calls: first provide `filePath` to receive upload instructions, upload locally, then call again with the returned `uploadRef`; do not send both fields together. Remote web URLs belong in `firecrawl_scrape`. Set `redactPII` to request redaction of personally identifiable information in the returned content. `zeroDataRetention` requires an eligible authenticated account; omit it for anonymous keyless use. Returns upload instructions for hosted phase one or parsed document content for the final call. Authenticated final responses can include a `data.metadata.scrapeId` for optional parse feedback.
| Parameter | Type | Description | |
|---|---|---|---|
formats | string[] | optional | |
jsonOptions | object | optional | |
queryOptions | object | optional | |
parsers | string[] | optional | |
pdfOptions | object | optional | |
onlyMainContent | boolean | optional | |
redactPII | boolean | optional | |
includeTags | string[] | optional | |
excludeTags | string[] | optional | |
removeBase64Images | boolean | optional | |
skipTlsVerification | boolean | optional | |
storeInCache | boolean | optional | |
zeroDataRetention | boolean | optional | |
maxAge | number | optional | Ignored: parse never reuses or stores indexed content. |
proxy | string | optional | One of: basic, auto |
filePath | string | optional | Phase 1 only: path to the local file on the caller/harness machine. Hosted MCP will not read or stat this path; it is used only to produce upload instructions. |
uploadRef | string | optional | Phase 2 only: short-lived upload reference returned by phase 1 after the local PUT upload completes. |
contentType | string | optional | Phase 1 MIME type override. If omitted, the server infers it from the file extension without reading the file. |
declaredSizeBytes | integer | optional | Optional phase 1 size declaration. Hosted MCP does not stat the file; provide this only if the caller already knows it. |
objective | string | optional | The user's underlying goal in one sentence, not a restatement of this call's arguments. Reuse it across related calls. Firecrawl uses it to learn what agents need and improve its results. No personal data, secrets or the user's exact words. |
conversationId | string | optional | conversationId from any earlier Firecrawl tool result in this conversation; after parallel calls, any one of theirs. Omit only on the first call of a conversation; the result returns one to pass on every later call. |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "firecrawl_parse",
"arguments": {}
}
}firecrawl_scraperead-onlyexternal accessScrape one URL and return its content: markdown by default, or HTML, links, screenshots, branding data, or a …
Scrape one URL and return its content: markdown by default, or HTML, links, screenshots, branding data, or a targeted answer. Use it when the request identifies a page and needs its content or defined fields: the user gives a URL or names a page or PDF and wants it read or summarized, or wants prices, specs, contact details or a table from it. Use `firecrawl_search` when additional web sources are needed; on an authenticated session, `firecrawl_map` lists a site's URLs and `firecrawl_crawl` collects a set of pages. `url` may omit the scheme (`example.com/page`); it is read as https. Firecrawl may serve recently indexed content; set `maxAge: 0` for a live fetch or a smaller `maxAge` to bound staleness. A successful response does not by itself confirm the page is still current. A named browser profile loads saved session data without saving changes to it. Authenticated responses can include a `metadata.scrapeId` for optional scrape feedback. On an authenticated session, `firecrawl_search` and `alexandria_library_search` can discover Alexandria providers for the same fields across several pages; a matching provider returns typed records in one `alexandria_library_read` call.
| Parameter | Type | Description | |
|---|---|---|---|
url | string | required | |
formats | string[] | optional | |
queryOptions | object | optional | |
screenshotOptions | object | optional | |
parsers | string[] | optional | |
pdfOptions | object | optional | |
onlyMainContent | boolean | optional | |
redactPII | boolean | optional | |
includeTags | string[] | optional | |
excludeTags | string[] | optional | |
waitFor | number | optional | |
mobile | boolean | optional | |
skipTlsVerification | boolean | optional | |
removeBase64Images | boolean | optional | |
location | object | optional | |
storeInCache | boolean | optional | |
zeroDataRetention | boolean | optional | |
maxAge | number | optional | |
lockdown | boolean | optional | |
proxy | string | optional | One of: basic, stealth, enhanced, auto |
profile | object | optional | Loads a saved browser profile without saving changes to it. |
timeout | integer | optional | Execution timeout in milliseconds. |
toolDetail | string | optional | Domain discovery detail, summary by default; compact returns provider/capability/description, full includes contracts. One of: compact, summary, full |
domainTools | boolean | optional | Include domain-matched Alexandria tools for the page in tools on the returned document. |
objective | string | required | The user's underlying goal in one sentence, not a restatement of this call's arguments. Reuse it across related calls. Firecrawl uses it to learn what agents need and improve its results. No personal data, secrets or the user's exact words. |
conversationId | string | optional | conversationId from any earlier Firecrawl tool result in this conversation; after parallel calls, any one of theirs. Omit only on the first call of a conversation; the result returns one to pass on every later call. |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "firecrawl_scrape",
"arguments": {
"url": "...",
"objective": "..."
}
}
}firecrawl_searchread-onlyexternal accessUse this when you need current or specific information from the web: recent events, latest releases and …
Use this when you need current or specific information from the web: recent events, latest releases and versions, prices, people and companies, statistics, or any fact that may have changed since your training data or that you are not sure of. Returns ranked results with query-relevant highlights; each web result is a title, URL, and description. Operators include quoted phrases, `-term`, `site:host`, `inurl:term`, `intitle:term`, and `related:host`; the set is non-exhaustive. `includeDomains` and `excludeDomains` are mutually exclusive hostname filters; categories limit result types to `research`, `pdf`, `developer`, or `gov`. For a programming question, add `categories: ["developer"]`. It searches an index of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and returns the results in `data.web` with `category: "developer"`. For a legal or regulatory question, `categories: ["gov"]` returns results in `data.web` with `category: "gov"` and cannot be combined with other categories; authenticated sessions also have `firecrawl_gov_search` as the dedicated tool. Verify gov results' issuer, jurisdiction, status, and version before citing current law. Authenticated search combines web results, semantic tool summaries and domain matches. Use sources: ["alexandria"] for semantic tools only. Authenticated searches always add alexandria to the sources, so sources: ["web"] also returns providers; domainTools: false turns off …
| Parameter | Type | Description | |
|---|---|---|---|
toolDetail | string | optional | Compact by default. Compact returns only provider, capability and description; full includes contracts. Read a selected tool's contract with alexandria_library_search. One of: compact, summary, full |
query | string | required | Query for web and semantic tool discovery. Operators include quoted phrases, `-term`, `site:host`, `inurl:term`, `intitle:term`, and `related:host`; the set is non-exhaustive. Browse the whole library with alexandria_library_search. |
domainTools | boolean | optional | Include domain-matched tools for result URLs. Defaults to true when Alexandria is combined with web, news or images; semantic-only search leaves domain matching off. |
highlights | boolean | optional | Return query-relevant page excerpts for web and news results when available (default). Highlights appear in web `description` and news `snippet`; otherwise, original snippets are returned. Set to false to keep the original search snippets. |
limit | integer | optional | |
tbs | string | optional | |
filter | string | optional | |
location | string | optional | |
includeDomains | string[] | optional | Hostnames to restrict results to. Mutually exclusive with excludeDomains. |
excludeDomains | string[] | optional | Hostnames to leave out of results. Mutually exclusive with includeDomains. |
sources | string | object[] | optional | Search sources; authenticated sessions default to web + alexandria, keyless sessions to web only. Authenticated searches always add alexandria to the sources, so sources: ["web"] also returns providers; domainTools: false turns off website-matched tools only. … |
categories | string[] | optional | Limit results to specific source types. `research` restricts ordinary web results to research-affiliated websites and returns page snippets, which is separate from the `firecrawl_research_*` tools that search paper abstracts and full text across biomedical … |
enterprise | string[] | optional | |
scrapeOptions | object | optional | Fetches the full page of every web result in the same call, and each fetched result is billed as a scrape. Leave it unset unless the task needs the full text of a few results: highlights usually answer, and firecrawl_scrape can fetch only the URLs you need. … |
objective | string | required | The user's underlying goal in one sentence, not a restatement of this call's arguments. Reuse it across related calls. Firecrawl uses it to learn what agents need and improve its results. No personal data, secrets or the user's exact words. |
conversationId | string | optional | conversationId from any earlier Firecrawl tool result in this conversation; after parallel calls, any one of theirs. Omit only on the first call of a conversation; the result returns one to pass on every later call. |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "firecrawl_search",
"arguments": {
"query": "...",
"objective": "..."
}
}
}Resources 2
FirecrawlBrowse data providers and view account credit usage.Firecrawl agentLive progress of a Firecrawl agent run.
Badge
Maintain this server? Put its live status in your README:
[](https://mcp.aianytime.net/s/firecrawl/)Edit this entry · Report a problem
More in Search & discovery
Checks record what a server answered, not whether it is safe. A listing is not a security audit; read a server's source and permissions before you connect it. Add a server · JSON · llms.txt · llms-full.txt
Browse: Agents, IDEs & developer tools · Search & discovery · Knowledge, memory & context · Media & generation · Security · Finance & markets · Marketing, content & social · Cloud, ops & data · Commerce, travel & logistics · Work & productivity · No account needed · Local servers