Firecrawl MCP Server

Researchstdiov1.6.0
代码仓库

MCP server for Firecrawl's web scraping and crawling API. Converts any website into clean, LLM-ready markdown or structured data. Supports single page scraping, multi-page crawling with depth control, sitemap-based extraction, and batch operations. Handles JavaScript-rendered pages, bypasses common anti-bot measures, and returns structured content suitable for RAG pipelines and knowledge base construction.

连接

将此配置添加到 .claude/mcp.json

{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "<YOUR_FIRECRAWL_API_KEY>"
      }
    }
  }
}

工具 (3)

firecrawl_scrape

Scrape a single URL and return clean markdown or structured content.

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "URL to scrape"
    },
    "formats": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Output formats (markdown, html, rawHtml, links, screenshot)"
    },
    "waitFor": {
      "type": "integer",
      "description": "Milliseconds to wait for JavaScript rendering"
    },
    "onlyMainContent": {
      "type": "boolean",
      "description": "Extract only the main content, removing nav/footer/ads"
    }
  }
}

firecrawl_crawl

Crawl a website starting from a URL, following links up to a specified depth.

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "Starting URL for the crawl"
    },
    "limit": {
      "type": "integer",
      "description": "Maximum number of pages to crawl"
    },
    "maxDepth": {
      "type": "integer",
      "description": "Maximum link depth to crawl (default 2)"
    },
    "excludePaths": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Skip URLs matching these glob patterns"
    },
    "includePaths": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Only crawl URLs matching these glob patterns"
    }
  }
}

firecrawl_map

Discover all URLs on a website using its sitemap or by crawling.

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "Website URL to map"
    },
    "limit": {
      "type": "integer",
      "description": "Maximum number of URLs to return"
    }
  }
}

资源

此服务器未提供任何资源。

提示词

此服务器未提供任何提示词。

服务器信息

作者
Mendable (@mendableai)
代码仓库
https://github.com/mendableai/firecrawl-mcp-server
许可证
MIT
版本
1.6.0
星标
3,250
最后更新
2026年5月26日