firecrawl/firecrawl-mcp-server

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

What it solves

Firecrawl MCP Server allows AI agents to interact with the live web. It solves the problem of agents being limited to their training data by providing tools to search, scrape, and interact with websites to get clean, structured, and agent-ready context.

How it works

It acts as a Model Context Protocol (MCP) server that connects AI agents to the Firecrawl API. The server exposes a wide range of tools that agents can call to perform web operations. These operations can be run via a hosted keyless free tier, an API-key authenticated cloud service, or a self-hosted Firecrawl instance.

Who it’s for

Developers building AI agents (using clients like Cursor, Windsurf, or Claude Desktop) who need their agents to have real-time web access, perform deep research, or extract structured data from websites.

Highlights

  • Web Search & Scraping: Search the web or scrape specific URLs into clean markdown or structured JSON based on a provided schema.
  • KNOWLEDGE-Specific Search: Dedicated search tools for developer documentation (GitHub issues, READMEs), US government publications, and scientific research papers.
  • Browser Automation: Ability to click, type, and navigate pages via the firecrawl_interact tool.
  • Autonomous Research: An agent tool for multi-source research that returns structured data from unknown or multiple sites.
  • Web Monitoring: Tools to check pages on a recurring schedule with diffs and change alerts.
  • Flexible Deployment: Supports hosted keyless access, API keys, OAuth, and self-hosted deployments via Docker or npx.

Related

  • Project
    brightdata/brightdata-mcp

    An MCP server that gives AI agents real-time web access with built-in bot detection bypass and 69 tools for web search, scraping, and structured data extraction.

  • Project
    spences10/mcp-omnisearch

    An MCP server that provides unified access to multiple web search, AI research, and web scraping providers like Tavily, Brave, and Firecrawl through a single interface.

  • Project
    exa-labs/exa-mcp-server

    An MCP server that connects AI agents to Exa for web search, content fetching, and multi-step research.

  • Project
    dbt-labs/dbt-mcp

    dbt‑MCP Server is an open‑source service that exposes a large catalog of dbt‑related tools (SQL execution, semantic‑layer queries, model discovery, dbt CLI commands, job administration, code generation, and documentation lookup) via the Model Context Protocol. It lets LLM‑powered agents understand and act on a dbt project—generating SQL from natural language, running dbt jobs, fetching lineage, and even creating new model files—making it a concrete bridge between data‑engineering metadata and AI assistants.

  • Project
    korotovsky/slack-mcp-server

    An MCP server that enables AI models to interact with Slack workspaces, allowing them to read, search, and manage messages, users, and channels.