Firecrawl
MCP server by Firecrawl
Search the web and scrape pages or files into clean markdown or structured JSON for LLM use.
Connect to Firecrawl
Sign-in is optional. Connect with Firecrawl’s own URL:
It works without signing in. Sign in with Firecrawl for more access.
Share this server
Opens this page, with the URL and setup steps.
mcp.tc/i/firecrawlAbout
Firecrawl connects an assistant to the Firecrawl web data service. The keyless hosted endpoint can search the web, scrape a single URL into markdown, HTML, links, screenshots or JSON that matches a schema, and parse local documents such as PDF, Word and spreadsheet files. Search also has categories for developer content (GitHub issues, pull requests, READMEs, docs) and research literature.
It runs as a hosted streamable HTTP endpoint at mcp.firecrawl.dev/v2/mcp, or locally through the firecrawl-mcp npm package. Keyless use has usage limits. Signing in with OAuth or sending an API key as a bearer token raises the limits and, depending on plan, adds tools such as map, crawl and agent.
What you can do
- Scrape a URL into markdown, HTML, links or screenshots
- Extract JSON that matches a supplied schema from a page
- Search web, news or image sources with ranked results
- Search indexed GitHub issues, pull requests and docs for coding questions
- Filter search to research-affiliated sites for biomedical and arXiv papers
- Parse PDF, Word, RTF and spreadsheet files into markdown or JSON
- Map and crawl sites with an API key or OAuth sign-in
Tools 3
firecrawl_scrapeRead-onlyScrape one URL and return markdown, HTML, links, screenshots or JSON matching a schema.
firecrawl_searchRead-onlySearch web, news or image sources and return ranked results with highlights.
firecrawl_parseRead-onlyParse a supported document such as PDF, Word or spreadsheet into markdown or JSON.
Read from the live server on 17 Nov 2026. Read-only, Writes and Can delete are hints the server declares; your client decides whether to ask before running a tool.
Example prompts
Scrape https://example.com/pricing and return it as markdown
Search the web for recent news on solid-state batteries
Extract product names and prices from this page as JSON
Find GitHub issues describing this error message
Set up
Every client connects to mcp.firecrawl.dev. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcp- Start Claude Code and type
/mcp. firecrawl should show as connected. To sign in for more access, pick it and choose Authenticate.
Add --scope user to make it available in every project, not just this one. Works without a key. An API key from Firecrawl raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
Claude Desktop
- Open Customize → Connectors, click + Add, then Add custom connector.
- Name it Firecrawl and paste this URL:
https://mcp.firecrawl.dev/v2/mcp- Click Add, then Connect. Signing in to Firecrawl is optional.
Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.
claude.ai
- Open the connector form on claude.ai. This button fills in the name and URL for you:
Add to claude.ai (opens in a new tab)
- Check that the URL reads
https://mcp.firecrawl.dev/v2/mcpand click Add. - Click Connect. Signing in to Firecrawl is optional.
Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.
ChatGPT
- On chatgpt.com, go to Plugins, select +, then Add custom MCP server.
- Enter a name for the server.
- Under Connection, paste
https://mcp.firecrawl.dev/v2/mcpas the server URL, then for authentication choose No authentication, or OAuth to sign in to Firecrawl for more access. - Check I understand and want to continue, then select Create as a plugin.
Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).
Cursor
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"firecrawl": {
"url": "https://mcp.firecrawl.dev/v2/mcp"
}
}
}Works without a key. An API key from Firecrawl raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
VS Code
Install in VS Code (opens in a new tab)
Or from a terminal:
code --add-mcp '{"name":"firecrawl","type":"http","url":"https://mcp.firecrawl.dev/v2/mcp"}'Or commit it to the repo in .vscode/mcp.json:
{
"servers": {
"firecrawl": {
"type": "http",
"url": "https://mcp.firecrawl.dev/v2/mcp"
}
}
}Works without a key. An API key from Firecrawl raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"firecrawl": {
"serverUrl": "https://mcp.firecrawl.dev/v2/mcp"
}
}
}- Refresh the MCP server list in Cascade.
Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers. Works without a key. An API key from Firecrawl raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
Codex
codex mcp add firecrawl --url https://mcp.firecrawl.dev/v2/mcpOr edit ~/.codex/config.toml directly:
[mcp_servers.firecrawl]
url = "https://mcp.firecrawl.dev/v2/mcp"Works without a key. An API key from Firecrawl raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
Gemini CLI
gemini mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcpThen, inside Gemini CLI, run /mcp auth firecrawl to sign in (optional).
This adds it to the current project. Add -s user to use it everywhere. Works without a key. An API key from Firecrawl raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
Any client
Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI’s settings file.
{
"mcpServers": {
"firecrawl": {
"type": "http",
"url": "https://mcp.firecrawl.dev/v2/mcp"
}
}
}Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.
Client only starts local servers? Bridge it with npx -y mcp-remote https://mcp.firecrawl.dev/v2/mcp.
Works without a key. An API key from Firecrawl raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
Embed
Show Firecrawl in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/firecrawl)<a href="https://mcp.tc/i/firecrawl"><img src="https://mcp.tc/i/firecrawl/badge.svg" alt="Firecrawl on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/firecrawl.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/firecrawl" title="Firecrawl on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/firecrawl.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Firecrawl card to your site.
Add the mcp.tc card for Firecrawl, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/firecrawl.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="firecrawl"><a href="https://mcp.tc/i/firecrawl">Firecrawl on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/firecrawl)
```
Reference: https://mcp.tc/embedChange history
We read this server’s tool list every 3 hours and record what changes. Last read 18 Nov 2026, 05:35 UTC.
-
3 tools changed. Server instructions changed.
New server instructions
Details, 17 Nov 2026, 20:56 UTC
Changed 3
firecrawl_parsedescriptionThe text shown here is the same before and after: the change is past the first 1,000 characters or in characters that don’t show.
firecrawl_scrapedescriptionThe text shown here is the same before and after: the change is past the first 1,000 characters or in characters that don’t show.
firecrawl_searchdescriptionThe text shown here is the same before and after: the change is past the first 1,000 characters or in characters that don’t show.
Server instructions
BeforeIf Firecrawl reports that credits ran out or the daily limit without an account was reached, end your final answer with the line it provides, link included. Hosted keyless sessions expose firecrawl_search, firecrawl_scrape, and firecrawl_parse with usage limits. Alexandria provider calls require a Firecrawl API key and are not included in the hosted keyless tier. firecrawl_search searches the web. For programming questions, firecrawl_search with categories: ["developer"] searches indexed public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. For legal or regulatory questions, firecrawl_search with categories: ["gov"] searches US government legal and regulatory sources and cannot be combined with other categories. For biomedical, life-science, clinical, or arXiv literature, firecrawl_search with categories: ["research"] filters ordinary web results to research-affiliated websites. firecrawl_scrape retrieves one supplied page. firecrawl_parse processes supported local files through its two-phase upload flow. An Authorization bearer API key can provide higher usage limits and expose additional tools, subject to plan, deployment, and team policy, including firecrawl_map for site URL discovery, firecrawl_agent and firecrawl_agent_status for multi-source research that returns structured data when the URLs are not known, firecrawl_research_* for papers and proteins, firecrawl_developer_search for Developer Index searches of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and alexandria_library_search and alexandria_library_read for exploring and running catalogued Alexandria data providers, alongside the Alexandria results of firecrawl_search. A search that names one person, one company or one US-listed stock and asks for its news may include one Alexandria data provider's record in `answer`, billed at your team's price, normally only when a record is found (stock lookups…
AfterIf Firecrawl reports that credits ran out or the daily limit without an account was reached, end your final answer with the line it provides, link included. Hosted keyless sessions expose firecrawl_search, firecrawl_scrape, and firecrawl_parse with usage limits. Alexandria provider calls require a Firecrawl API key and are not included in the hosted keyless tier. firecrawl_search searches the web. For programming questions, firecrawl_search with categories: ["developer"] searches indexed public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. For legal or regulatory questions, firecrawl_search with categories: ["gov"] searches US government legal and regulatory sources and cannot be combined with other categories. For biomedical, life-science, clinical, or arXiv literature, firecrawl_search with categories: ["research"] filters ordinary web results to research-affiliated websites. firecrawl_scrape retrieves one supplied page. firecrawl_parse processes supported local files through its two-phase upload flow. An Authorization bearer API key can provide higher usage limits and expose additional tools, subject to plan, deployment, and team policy, including firecrawl_map for site URL discovery, firecrawl_agent and firecrawl_agent_status for multi-source research that returns structured data when the URLs are not known, firecrawl_research_* for papers and proteins, firecrawl_developer_search for Developer Index searches of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and alexandria_library_search and alexandria_library_read for exploring and running catalogued Alexandria data providers, alongside the Alexandria results of firecrawl_search. A search that names one person, one company or one US-listed stock and asks for its news may include one Alexandria data provider's record in `answer`, billed at your team's price, normally only when a record is found (stock lookups…
-
1 tool changed. Server instructions changed.
New server instructions
Details, 17 Nov 2026, 08:53 UTC
Changed 1
firecrawl_searchinput schema- Removed parameters:
answerShowTitle
- Removed parameters:
Server instructions
BeforeIf Firecrawl reports that credits ran out or the daily limit without an account was reached, end your final answer with the line it provides, link included. Hosted keyless sessions expose firecrawl_search, firecrawl_scrape, and firecrawl_parse with usage limits. Alexandria provider calls require a Firecrawl API key and are not included in the hosted keyless tier. firecrawl_search searches the web. For programming questions, firecrawl_search with categories: ["developer"] searches indexed public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. For legal or regulatory questions, firecrawl_search with categories: ["gov"] searches US government legal and regulatory sources and cannot be combined with other categories. For biomedical, life-science, clinical, or arXiv literature, firecrawl_search with categories: ["research"] filters ordinary web results to research-affiliated websites. firecrawl_scrape retrieves one supplied page. firecrawl_parse processes supported local files through its two-phase upload flow. An Authorization bearer API key can provide higher usage limits and expose additional tools, subject to plan, deployment, and team policy, including firecrawl_map for site URL discovery, firecrawl_agent and firecrawl_agent_status for multi-source research that returns structured data when the URLs are not known, firecrawl_research_* for papers and proteins, firecrawl_developer_search for Developer Index searches of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and alexandria_library_search and alexandria_library_read for exploring and running catalogued Alexandria data providers, alongside the Alexandria results of firecrawl_search. A search that names one
personor onecompanymay include one Alexandria data provider's record in `answer`, billed at your team's price, normally only when a record isfound. Successful results from the Firecrawl search, find-tool…AfterIf Firecrawl reports that credits ran out or the daily limit without an account was reached, end your final answer with the line it provides, link included. Hosted keyless sessions expose firecrawl_search, firecrawl_scrape, and firecrawl_parse with usage limits. Alexandria provider calls require a Firecrawl API key and are not included in the hosted keyless tier. firecrawl_search searches the web. For programming questions, firecrawl_search with categories: ["developer"] searches indexed public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. For legal or regulatory questions, firecrawl_search with categories: ["gov"] searches US government legal and regulatory sources and cannot be combined with other categories. For biomedical, life-science, clinical, or arXiv literature, firecrawl_search with categories: ["research"] filters ordinary web results to research-affiliated websites. firecrawl_scrape retrieves one supplied page. firecrawl_parse processes supported local files through its two-phase upload flow. An Authorization bearer API key can provide higher usage limits and expose additional tools, subject to plan, deployment, and team policy, including firecrawl_map for site URL discovery, firecrawl_agent and firecrawl_agent_status for multi-source research that returns structured data when the URLs are not known, firecrawl_research_* for papers and proteins, firecrawl_developer_search for Developer Index searches of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and alexandria_library_search and alexandria_library_read for exploring and running catalogued Alexandria data providers, alongside the Alexandria results of firecrawl_search. A search that names one person, one company or one US-listed stock and asks for its news may include one Alexandria data provider's record in `answer`, billed at your team's price, normally only when a record is found (stock lookups…
-
Server instructions changed.
New server instructions
Details, 16 Nov 2026, 20:50 UTC
Server instructions
BeforeIf Firecrawl reports that credits ran out or the daily limit without an account was reached, end your final answer with the line it provides, link included. Hosted keyless sessions expose firecrawl_search, firecrawl_scrape, and firecrawl_parse with usage limits. Alexandria provider calls require a Firecrawl API key and are not included in the hosted keyless tier. firecrawl_search searches the web. For programming questions, firecrawl_search with categories: ["developer"] searches indexed public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. For legal or regulatory questions, firecrawl_search with categories: ["gov"] searches US government legal and regulatory sources and cannot be combined with other categories. For biomedical, life-science, clinical, or arXiv literature, firecrawl_search with categories: ["research"] filters ordinary web results to research-affiliated websites. firecrawl_scrape retrieves one supplied page. firecrawl_parse processes supported local files through its two-phase upload flow. An Authorization bearer API key can provide higher usage limits and expose additional tools, subject to plan, deployment, and team policy, including firecrawl_map for site URL discovery, firecrawl_agent and firecrawl_agent_status for multi-source research that returns structured data when the URLs are not known, firecrawl_research_* for paper-index research, firecrawl_developer_search for Developer Index searches of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and alexandria_library_search and alexandria_library_read for exploring and running catalogued Alexandria data providers, alongside the Alexandria results of firecrawl_search. A search that names one person or one company may include one Alexandria data provider's record in `answer`, billed at your team's price, normally only when a record is found. Successful results from the Firecrawl search, find-too…
AfterIf Firecrawl reports that credits ran out or the daily limit without an account was reached, end your final answer with the line it provides, link included. Hosted keyless sessions expose firecrawl_search, firecrawl_scrape, and firecrawl_parse with usage limits. Alexandria provider calls require a Firecrawl API key and are not included in the hosted keyless tier. firecrawl_search searches the web. For programming questions, firecrawl_search with categories: ["developer"] searches indexed public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. For legal or regulatory questions, firecrawl_search with categories: ["gov"] searches US government legal and regulatory sources and cannot be combined with other categories. For biomedical, life-science, clinical, or arXiv literature, firecrawl_search with categories: ["research"] filters ordinary web results to research-affiliated websites. firecrawl_scrape retrieves one supplied page. firecrawl_parse processes supported local files through its two-phase upload flow. An Authorization bearer API key can provide higher usage limits and expose additional tools, subject to plan, deployment, and team policy, including firecrawl_map for site URL discovery, firecrawl_agent and firecrawl_agent_status for multi-source research that returns structured data when the URLs are not known, firecrawl_research_* for papers and proteins, firecrawl_developer_search for Developer Index searches of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and alexandria_library_search and alexandria_library_read for exploring and running catalogued Alexandria data providers, alongside the Alexandria results of firecrawl_search. A search that names one person or one company may include one Alexandria data provider's record in `answer`, billed at your team's price, normally only when a record is found. Successful results from the Firecrawl search, find-tool…
-
1 tool changed.
Newly required parameter
Details, 16 Nov 2026, 17:53 UTC
Changed 1
firecrawl_scrapedescription and input schemaThe text shown here is the same before and after: the change is past the first 1,000 characters or in characters that don’t show.
- Removed parameters:
requestIdalexandria - Now required:
url - Description of
toolDetailBeforeURL mode only: domaindiscovery detail, summary by default; compact returns provider/capability/description, full includes contracts.Ignored with alexandria.AfterDomain discovery detail, summary by default; compact returns provider/capability/description, full includes contracts.
- Description of
domainToolsBeforeURL mode only: includedomain-matched Alexandria tools for the page in tools on the returned document.Ignored with alexandria.AfterInclude domain-matched Alexandria tools for the page in tools on the returned document.
- Removed parameters:
-
1 tool changed. Server instructions changed.
New server instructions
Details, 16 Nov 2026, 05:57 UTC
Changed 1
firecrawl_searchinput schema and output schema- New parameters:
answerShowTitle
- New parameters:
Server instructions
BeforeIf Firecrawl reports that credits ran out or the daily limit without an account was reached, end your final answer with the line it provides, link included. Hosted keyless sessions expose firecrawl_search, firecrawl_scrape, and firecrawl_parse with usage limits. Alexandria provider calls require a Firecrawl API key and are not included in the hosted keyless tier. firecrawl_search searches the web. For programming questions, firecrawl_search with categories: ["developer"] searches indexed public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. For legal or regulatory questions, firecrawl_search with categories: ["gov"] searches US government legal and regulatory sources and cannot be combined with other categories. For biomedical, life-science, clinical, or arXiv literature, firecrawl_search with categories: ["research"] filters ordinary web results to research-affiliated websites. firecrawl_scrape retrieves one supplied page. firecrawl_parse processes supported local files through its two-phase upload flow. An Authorization bearer API key can provide higher usage limits and expose additional tools, subject to plan, deployment, and team policy, including firecrawl_map for site URL discovery, firecrawl_agent and firecrawl_agent_status for multi-source research that returns structured data when the URLs are not known, firecrawl_research_* for paper-index research, firecrawl_developer_search for Developer Index searches of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and alexandria_library_search and alexandria_library_read for exploring and running catalogued Alexandria data providers, alongside the Alexandria results of firecrawl_search. Successful results from the Firecrawl search,
find-tools, Alexandria library, scrape, map, crawl, agent, interact, parse and feedback tools include a conversationId. Pass it as conversationId on every later call to those tools in t…AfterIf Firecrawl reports that credits ran out or the daily limit without an account was reached, end your final answer with the line it provides, link included. Hosted keyless sessions expose firecrawl_search, firecrawl_scrape, and firecrawl_parse with usage limits. Alexandria provider calls require a Firecrawl API key and are not included in the hosted keyless tier. firecrawl_search searches the web. For programming questions, firecrawl_search with categories: ["developer"] searches indexed public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. For legal or regulatory questions, firecrawl_search with categories: ["gov"] searches US government legal and regulatory sources and cannot be combined with other categories. For biomedical, life-science, clinical, or arXiv literature, firecrawl_search with categories: ["research"] filters ordinary web results to research-affiliated websites. firecrawl_scrape retrieves one supplied page. firecrawl_parse processes supported local files through its two-phase upload flow. An Authorization bearer API key can provide higher usage limits and expose additional tools, subject to plan, deployment, and team policy, including firecrawl_map for site URL discovery, firecrawl_agent and firecrawl_agent_status for multi-source research that returns structured data when the URLs are not known, firecrawl_research_* for paper-index research, firecrawl_developer_search for Developer Index searches of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and alexandria_library_search and alexandria_library_read for exploring and running catalogued Alexandria data providers, alongside the Alexandria results of firecrawl_search. A search that names one person or one company may include one Alexandria data provider's record in `answer`, billed at your team's price, normally only when a record is found. Successful results from the Firecrawl search, find-too…
-
1 tool changed.
Details, 13 Nov 2026, 23:55 UTC
Changed 1
firecrawl_searchoutput schema
-
New version 3.40.0 (was 3.39.0). Reported by the server.
-
1 tool changed. Server instructions changed.
New server instructions
Details, 11 Nov 2026, 17:53 UTC
Changed 1
firecrawl_searchoutput schema
Server instructions
BeforeIf Firecrawl reports that credits ran out or the daily limit without an account was reached, end your final answer with the line it provides, link included. Hosted keyless sessions expose firecrawl_search, firecrawl_scrape, and firecrawl_parse with usage limits. Alexandria provider calls require a Firecrawl API key and are not included in the hosted keyless tier. firecrawl_search searches the web. For programming questions, firecrawl_search with categories: ["developer"] searches indexed public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. For legal or regulatory questions, firecrawl_search with categories: ["gov"] searches US government legal and regulatory sources and cannot be combined with other categories. For biomedical, life-science, clinical, or arXiv literature, firecrawl_search with categories: ["research"] filters ordinary web results to research-affiliated websites. firecrawl_scrape retrieves one supplied page. firecrawl_parse processes supported local files through its two-phase upload flow. An Authorization bearer API key can provide higher usage limits and expose additional tools, subject to plan, deployment, and team policy, including firecrawl_map for site URL discovery, firecrawl_agent and firecrawl_agent_status for multi-source research that returns structured data when the URLs are not known, firecrawl_research_* for paper-index research, firecrawl_developer_search for Developer Index searches of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and alexandria_library_search and alexandria_library_read for exploring and running catalogued Alexandria data providers, alongside the Alexandria results of firecrawl_search. Successful results from the Firecrawl search, find-tools, scrape, map, crawl, agent, interact, parse and feedback tools include a conversationId. Pass it as conversationId on every later call to those tools in the same conversation…
AfterIf Firecrawl reports that credits ran out or the daily limit without an account was reached, end your final answer with the line it provides, link included. Hosted keyless sessions expose firecrawl_search, firecrawl_scrape, and firecrawl_parse with usage limits. Alexandria provider calls require a Firecrawl API key and are not included in the hosted keyless tier. firecrawl_search searches the web. For programming questions, firecrawl_search with categories: ["developer"] searches indexed public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. For legal or regulatory questions, firecrawl_search with categories: ["gov"] searches US government legal and regulatory sources and cannot be combined with other categories. For biomedical, life-science, clinical, or arXiv literature, firecrawl_search with categories: ["research"] filters ordinary web results to research-affiliated websites. firecrawl_scrape retrieves one supplied page. firecrawl_parse processes supported local files through its two-phase upload flow. An Authorization bearer API key can provide higher usage limits and expose additional tools, subject to plan, deployment, and team policy, including firecrawl_map for site URL discovery, firecrawl_agent and firecrawl_agent_status for multi-source research that returns structured data when the URLs are not known, firecrawl_research_* for paper-index research, firecrawl_developer_search for Developer Index searches of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and alexandria_library_search and alexandria_library_read for exploring and running catalogued Alexandria data providers, alongside the Alexandria results of firecrawl_search. Successful results from the Firecrawl search, find-tools, Alexandria library, scrape, map, crawl, agent, interact, parse and feedback tools include a conversationId. Pass it as conversationId on every later call to those tools in t…
-
1 tool changed. Server instructions changed.
New server instructions
Details, 11 Nov 2026, 08:51 UTC
Changed 1
firecrawl_searchdescription and input schemaThe text shown here is the same before and after: the change is past the first 1,000 characters or in characters that don’t show.
- Description of
toolDetailBeforeCompact by default. Compact returns only provider, capability and description; full includes contracts. Inspect selected compact tools with firecrawl_find_tools providers and capabilities.
AfterCompact by default. Compact returns only provider, capability and description; full includes contracts. Read a selected tool's contract with alexandria_library_search.
- Description of
queryBeforeQuery 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. Catalogue browsing is a…
AfterQuery 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 librar…
- Description of
Server instructions
BeforeIf Firecrawl reports that credits ran out or the daily limit without an account was reached, end your final answer with the line it provides, link included. Hosted keyless sessions expose firecrawl_search, firecrawl_scrape, and firecrawl_parse with usage limits. Alexandria provider calls require a Firecrawl API key and are not included in the hosted keyless tier. firecrawl_search searches the web. For programming questions, firecrawl_search with categories: ["developer"] searches indexed public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. For legal or regulatory questions, firecrawl_search with categories: ["gov"] searches US government legal and regulatory sources and cannot be combined with other categories. For biomedical, life-science, clinical, or arXiv literature, firecrawl_search with categories: ["research"] filters ordinary web results to research-affiliated websites. firecrawl_scrape retrieves one supplied page. firecrawl_parse processes supported local files through its two-phase upload flow. An Authorization bearer API key can provide higher usage limits and expose additional tools, subject to plan, deployment, and team policy, including firecrawl_map for site URL discovery, firecrawl_agent and firecrawl_agent_status for multi-source research that returns structured data when the URLs are not known, firecrawl_research_* for paper-index research, firecrawl_developer_search for Developer Index searches of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and firecrawl_find_tools as the progressive Alexandria catalogue lookup alongside the Alexandria options of firecrawl_search and firecrawl_scrape for catalogued data providers. Successful results from the Firecrawl search, find-tools, scrape, map, crawl, agent, interact, parse and feedback tools include a conversationId. Pass it as conversationId on every later call to those tools in the same conversatio…
AfterIf Firecrawl reports that credits ran out or the daily limit without an account was reached, end your final answer with the line it provides, link included. Hosted keyless sessions expose firecrawl_search, firecrawl_scrape, and firecrawl_parse with usage limits. Alexandria provider calls require a Firecrawl API key and are not included in the hosted keyless tier. firecrawl_search searches the web. For programming questions, firecrawl_search with categories: ["developer"] searches indexed public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. For legal or regulatory questions, firecrawl_search with categories: ["gov"] searches US government legal and regulatory sources and cannot be combined with other categories. For biomedical, life-science, clinical, or arXiv literature, firecrawl_search with categories: ["research"] filters ordinary web results to research-affiliated websites. firecrawl_scrape retrieves one supplied page. firecrawl_parse processes supported local files through its two-phase upload flow. An Authorization bearer API key can provide higher usage limits and expose additional tools, subject to plan, deployment, and team policy, including firecrawl_map for site URL discovery, firecrawl_agent and firecrawl_agent_status for multi-source research that returns structured data when the URLs are not known, firecrawl_research_* for paper-index research, firecrawl_developer_search for Developer Index searches of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and alexandria_library_search and alexandria_library_read for exploring and running catalogued Alexandria data providers, alongside the Alexandria results of firecrawl_search. Successful results from the Firecrawl search, find-tools, scrape, map, crawl, agent, interact, parse and feedback tools include a conversationId. Pass it as conversationId on every later call to those tools in the same conversation…
-
New version 3.39.0 (was 3.38.0). Reported by the server.
-
1 tool changed. Server instructions changed.
New server instructions
Details, 10 Nov 2026, 20:46 UTC
Changed 1
firecrawl_scrapeThe 10 newest entries show every detail; older ones show names only.
-
1 tool changed.
Details, 10 Nov 2026, 08:49 UTC
Changed 1
firecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
1 tool changed.
Details, 10 Nov 2026, 05:48 UTC
Changed 1
firecrawl_scrapeThe 10 newest entries show every detail; older ones show names only.
-
1 tool changed.
Details, 8 Nov 2026, 02:52 UTC
Changed 1
firecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
New version 3.38.0 (was 3.37.0). Reported by the server.
-
1 tool changed.
Details, 6 Nov 2026, 23:42 UTC
Changed 1
firecrawl_scrapeThe 10 newest entries show every detail; older ones show names only.
-
1 tool changed.
Details, 6 Nov 2026, 17:53 UTC
Changed 1
firecrawl_scrapeThe 10 newest entries show every detail; older ones show names only.
-
Server instructions changed.
New server instructions
-
3 tools changed.
Details, 5 Nov 2026, 02:52 UTC
Changed 3
firecrawl_parsefirecrawl_scrapefirecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
Server instructions changed.
New server instructions
-
Server instructions changed.
New server instructions
-
Server instructions changed.
New server instructions
-
New version 3.36.1 (was 3.36.0). Reported by the server.
-
3 tools changed. Server instructions changed.
New server instructions
Details, 31 Oct 2026, 20:47 UTC
Changed 3
firecrawl_parsefirecrawl_scrapefirecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
New version 3.36.0 (was 3.35.0). Reported by the server.
-
3 tools changed.
Details, 28 Oct 2026, 00:01 UTC
Changed 3
firecrawl_parsefirecrawl_scrapefirecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
1 tool changed.
Details, 27 Oct 2026, 21:03 UTC
Changed 1
firecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
New version 3.35.0 (was 3.34.1). Reported by the server.
-
New version 3.34.0 (was 3.33.4). Reported by the server.
-
1 tool changed. Server instructions changed.
New server instructions
Details, 22 Oct 2026, 16:42 UTC
Changed 1
firecrawl_scrapeThe 10 newest entries show every detail; older ones show names only.
-
1 tool changed.
Details, 21 Oct 2026, 07:40 UTC
Changed 1
firecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
New version 3.33.4 (was 3.33.3). Reported by the server.
-
2 tools changed. Server instructions changed.
New server instructions
Details, 21 Oct 2026, 01:35 UTC
Changed 2
firecrawl_scrapefirecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
New version 3.31.0 (was 3.30.3). Reported by the server.
-
2 tools changed.
Newly required parameter
Details, 17 Oct 2026, 22:33 UTC
Changed 2
firecrawl_scrapefirecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
New version 3.30.3 (was 3.30.2). Reported by the server.
-
2 tools changed.
Details, 17 Oct 2026, 01:34 UTC
Changed 2
firecrawl_scrapefirecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
New version 3.30.1 (was 3.30.0). Reported by the server.
-
2 tools changed.
Details, 14 Oct 2026, 19:38 UTC
Changed 2
firecrawl_scrapefirecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
New version 3.30.0 (was 3.29.1). Reported by the server.
-
3 tools changed.
Details, 13 Oct 2026, 19:35 UTC
Changed 3
firecrawl_parsefirecrawl_scrapefirecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
2 tools changed.
Newly required parameter
Details, 13 Oct 2026, 01:37 UTC
Changed 2
firecrawl_scrapefirecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
1 tool changed.
Details, 12 Oct 2026, 22:31 UTC
Changed 1
firecrawl_scrapeThe 10 newest entries show every detail; older ones show names only.
-
2 tools changed.
Details, 9 Oct 2026, 10:35 UTC
Changed 2
firecrawl_scrapefirecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
New version 3.29.0 (was 3.28.2). Reported by the server.
-
1 tool changed.
Details, 8 Oct 2026, 19:32 UTC
Changed 1
firecrawl_searchThe 10 newest entries show every detail; older ones show names only.
-
New version 3.28.2 (was 3.28.1). Reported by the server.
-
Tracking started: 3 tools.
FAQ
Can I paste mcp.tc/i/firecrawl into my MCP client?
No. mcp.tc links are pages, not server addresses. Connect with https://mcp.firecrawl.dev/v2/mcp, so your client talks to Firecrawl directly. The quick link is for sharing: it opens this page, with setup steps for every client.
Does Firecrawl need an API key or a sign-in?
Not to start. Firecrawl works without signing in and offers sign-in for more access.
Is Firecrawl a remote or a local server?
Remote. Firecrawl hosts it at https://mcp.firecrawl.dev/v2/mcp, and it speaks Streamable HTTP. There’s nothing to install.
What can Firecrawl do?
It has 3 tools: firecrawl_scrape, firecrawl_search and firecrawl_parse. You can scrape a URL into markdown, HTML, links or screenshots, extract JSON that matches a supplied schema from a page and search web, news or image sources with ranked results.
Which clients can use it?
Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.
Does mcp.tc track changes to Firecrawl?
Yes. Firecrawl’s History tab shows each change we find to its tools, down to descriptions and parameters, plus new versions and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read Firecrawl’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with Firecrawl. This page was built from Firecrawl’s public metadata, last checked on 17 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.