# Firecrawl MCP Server (MCP server) > Firecrawl MCP Server is an MCP server that brings Firecrawl to MCP-compatible AI agents — search, scrape, and interact with the live web for clean, agent-ready context. It has 7,564 GitHub stars, is released under the MIT license and runs locally with npx -y firecrawl-mcp. 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. ## Key facts | Fact | Value | |---|---| | Repository | https://github.com/firecrawl/firecrawl-mcp-server | | GitHub stars | 7,564 | | License | MIT | | Language | JavaScript | | Transport | stdio, streamable-http | | Packages | npm: firecrawl-mcp | | Remote URL | https://mcp.firecrawl.dev/v2/mcp | | Needs API key | yes | | Official | no | | Works with | Claude Desktop, Claude Code, Cursor, VS Code, Claude.ai, ChatGPT | | Category | Web & browsing | | Latest release | v3.2.1 (Sep 26, 2025) | | Last commit | Oct 6, 2026 | | MCP registry name | io.github.firecrawl/firecrawl-mcp-server | ## Install ### Claude Desktop (claude_desktop_config.json) ```json { "mcpServers": { "firecrawl-mcp-server": { "command": "npx", "args": [ "-y", "firecrawl-mcp" ], "env": { "FIRECRAWL_API_KEY": "your-value" } } } } ``` Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards. ### Claude Code ```sh claude mcp add --env FIRECRAWL_API_KEY=your-value --transport stdio firecrawl-mcp-server -- npx -y firecrawl-mcp ``` ### Cursor (.cursor/mcp.json) ```json { "mcpServers": { "firecrawl-mcp-server": { "type": "stdio", "command": "npx", "args": [ "-y", "firecrawl-mcp" ], "env": { "FIRECRAWL_API_KEY": "your-value" } } } } ``` Project file; use ~/.cursor/mcp.json to enable it in every project. ### VS Code (.vscode/mcp.json) ```json { "inputs": [ { "type": "promptString", "id": "firecrawl_api_key", "description": "FIRECRAWL_API_KEY", "password": true } ], "servers": { "firecrawl-mcp-server": { "type": "stdio", "command": "npx", "args": [ "-y", "firecrawl-mcp" ], "env": { "FIRECRAWL_API_KEY": "${input:firecrawl_api_key}" } } } } ``` ### Claude Code (remote) ```sh claude mcp add --transport http firecrawl-mcp-server "https://mcp.firecrawl.dev/v2/mcp" ``` The same server is also hosted as a remote MCP endpoint, so nothing runs on your machine. Config formats checked against the official docs on 2026-10-07. ## Environment variables - `FIRECRAWL_API_KEY` (secret): Your API key for Firecrawl ## Tools - `prompt`: Natural language description of the data you want (required, max 10,000 characters) - `urls`: Optional array of URLs to focus the agent on specific pages - `schema`: Optional JSON schema for structured output - `effort`: Optional. "low", "medium" or "high" reasoning budget for the agent task. - `mode`: Optional. "extract" (default) returns the complete structured result every turn. - `exchange`: Optional. Alexandria provider settings for this turn, forwarded as-is to POST /v2/agent: - `enabled`: , toolkits (up to 5 provider slugs), maxCalls (1 to 30), requireApproval (paid calls end the turn with a… - `approve`: { approvalId, callIds?, always? } answers yes to the pendingApproval the previous turn ended on. - `decline`: { approvalId } answers no. A declined terms offer keeps those providers out of the rest of the thread. - `processing`: Agent is still researching - check back later - `completed`: Research finished - response includes the extracted data - `failed`: An error occurred - `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. - `query`: the developer question or search phrase. - `skills`: set to "only" to search agent-skill files alone. - `firecrawl_credit_usage`: defaults to { "view": "current" } and returns remainingCredits, planCredits, billingPeriodStart, and billingPeriodEnd. ## Similar MCP servers - [Browser Use](https://appsgit.com/mcp-servers/browser-use): Control a real Chrome browser to complete any task: fill forms, extract data, book flights. (117,307 stars, MIT, official) - [Scrapling MCP Server](https://appsgit.com/mcp-servers/scrapling-mcp-server): Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. (86,017 stars, BSD-3-Clause) - [Chrome DevTools MCP](https://appsgit.com/mcp-servers/chrome-devtools-mcp): MCP server for Chrome DevTools. (53,049 stars, Apache-2.0) - [Bytedance Browser](https://appsgit.com/mcp-servers/bytedance-browser): MCP server for browser use access. (39,206 stars, Apache-2.0) - [Bytedance Commands](https://appsgit.com/mcp-servers/bytedance-commands): An MCP server to run arbitrary commands. (39,206 stars, Apache-2.0) - [Bytedance Search](https://appsgit.com/mcp-servers/bytedance-search): MCP server for web search operations. (39,206 stars, Apache-2.0) --- Canonical page: https://appsgit.com/mcp-servers/firecrawl-mcp-server Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed nightly. Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.