Skip to main content
Glama
enesjakozh
Msparihar

MCP Server Firecrawl

by Msparihar
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Firecrawl MCP 服务器

使用 Firecrawl API 进行网页抓取、内容搜索、站点爬取和数据提取的模型上下文协议 (MCP) 服务器。

特征

  • 网页抓取：使用可自定义的选项从任何网页提取内容

    • 移动设备模拟

    • 广告和弹出窗口拦截

    • 内容过滤

    • 结构化数据提取

    • 多种输出格式

  • 内容搜索：智能搜索功能

    • 多语言支持

    • 基于位置的结果

    • 可定制的结果限制

    • 结构化输出格式

  • 网站爬取：高级网页爬取功能

    • 深度控制

    • 路径过滤

    • 速率限制

    • 进度追踪

    • 网站地图集成

  • 站点映射：生成站点结构图

    • 子域名支持

    • 搜索过滤

    • 链接分析

    • 视觉层次

  • 数据提取：从多个 URL 中提取结构化数据

    • 架构验证

    • 批处理

    • 网络搜索丰富

    • 自定义提取提示

Related MCP server: MCP Firecrawl Server

安装

# Global installation
npm install -g @modelcontextprotocol/mcp-server-firecrawl

# Local project installation
npm install @modelcontextprotocol/mcp-server-firecrawl

快速入门

  1. 从开发者门户获取您的 Firecrawl API 密钥

  2. 设置您的 API 密钥：

    Unix/Linux/macOS（bash/zsh）：

    export FIRECRAWL_API_KEY=your-api-key

    Windows（命令提示符）：

    set FIRECRAWL_API_KEY=your-api-key

    Windows（PowerShell）：

    $env:FIRECRAWL_API_KEY = "your-api-key"

    替代方案：使用 .env 文件（推荐用于开发）：

    # Install dotenv
npm install dotenv

# Create .env file
echo "FIRECRAWL_API_KEY=your-api-key" > .env

    然后在你的代码中：

    import dotenv from 'dotenv';
dotenv.config();

  3. 运行服务器：

    mcp-server-firecrawl

一体化

克劳德桌面应用程序

添加到您的 MCP 设置：

{
  "firecrawl": {
    "command": "mcp-server-firecrawl",
    "env": {
      "FIRECRAWL_API_KEY": "your-api-key"
    }
  }
}

Claude VSCode 扩展

添加到您的 MCP 配置：

{
  "mcpServers": {
    "firecrawl": {
      "command": "mcp-server-firecrawl",
      "env": {
        "FIRECRAWL_API_KEY": "your-api-key"
      }
    }
  }
}

使用示例

网页抓取

// Basic scraping
{
  name: "scrape_url",
  arguments: {
    url: "https://example.com",
    formats: ["markdown"],
    onlyMainContent: true
  }
}

// Advanced extraction
{
  name: "scrape_url",
  arguments: {
    url: "https://example.com/blog",
    jsonOptions: {
      prompt: "Extract article content",
      schema: {
        title: "string",
        content: "string"
      }
    },
    mobile: true,
    blockAds: true
  }
}

网站抓取

// Basic crawling
{
  name: "crawl",
  arguments: {
    url: "https://example.com",
    maxDepth: 2,
    limit: 100
  }
}

// Advanced crawling
{
  name: "crawl",
  arguments: {
    url: "https://example.com",
    maxDepth: 3,
    includePaths: ["/blog", "/products"],
    excludePaths: ["/admin"],
    ignoreQueryParameters: true
  }
}

站点地图

// Generate site map
{
  name: "map",
  arguments: {
    url: "https://example.com",
    includeSubdomains: true,
    limit: 1000
  }
}

数据提取

// Extract structured data
{
  name: "extract",
  arguments: {
    urls: ["https://example.com/product1", "https://example.com/product2"],
    prompt: "Extract product details",
    schema: {
      name: "string",
      price: "number",
      description: "string"
    }
  }
}

配置

有关详细的设置选项，请参阅配置指南。

API 文档

有关详细的端点规范，请参阅API 文档。

发展

# Install dependencies
npm install

# Build
npm run build

# Run tests
npm test

# Start in development mode
npm run dev

示例

查看示例目录以获取更多使用示例：

错误处理

服务器实现了强大的错误处理：

  • 使用指数退避算法进行速率限制

  • 自动重试

  • 详细错误消息

  • 调试日志记录

安全

  • API 密钥保护

  • 请求验证

  • 域名允许列表

  • 速率限制

  • 安全错误消息

贡献

请参阅CONTRIBUTING.md了解贡献指南。

执照

MIT 许可证 - 详情请参阅许可证。

Available Tools

2 tools
extractC

Extracts structured data from URLs

ParametersJSON Schema
NameRequiredDescriptionDefault
urlsYesURLs to extract from
promptNoExtraction guidance prompt
schemaNoData structure schema
ignoreSitemapNoIgnore sitemap.xml during processing
enableWebSearchNoUse web search for additional data
includeSubdomainsNoInclude subdomains in processing

TDQS

C2.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description must disclose behavior. It does not mention network requests, rate limits, authentication, error handling, or whether it is idempotent. Only states 'extracts', which is vague.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Very short at 7 words, but under-specified. Lacks structure such as sections or examples. Conciseness would be appropriate if complete, but here it is insufficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (6 parameters, nested objects, sibling tools, no output schema), the description is extremely incomplete. No information on return format, usage patterns, or edge cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description does not add any extra meaning beyond the schema's parameter descriptions. No elaboration on how parameters interact.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool extracts structured data from URLs, but does not differentiate from sibling 'map'. The verb and resource are clear, but the scope is vague as 'structured data' is not defined.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like 'map', no prerequisites or exclusions provided. The description is insufficient for an agent to decide usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

mapC

Maps a website's structure

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesBase URL to map
limitNoMaximum links to return
searchNoSearch query for mapping
timeoutNoRequest timeout
sitemapOnlyNoOnly use sitemap.xml for mapping
ignoreSitemapNoIgnore sitemap.xml during mapping
includeSubdomainsNoInclude subdomains in mapping

TDQS

C2.4/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description must disclose behavioral traits. It only says 'Maps a website's structure' with no details on whether it crawls, destructiveness, rate limits, or return format. This is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, short sentence, which is efficient but under-specified for a tool with 7 parameters. It could include key details without sacrificing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (7 parameters, no output schema, no annotations), the description lacks essential context such as return values, process details, or limitations. It is highly incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for all 7 parameters, so the baseline is 3. The description adds no additional meaning beyond the schema, making it adequate but not improved.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Maps') and resource ('a website's structure'), making the core purpose clear. However, it does not differentiate from the sibling tool 'extract', which could lead to ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives (e.g., 'extract'). The description lacks context for selection or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.0.1
    • First observedextract
    • First observedmap
Deploy Server
Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

TDQS

C2.7/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one extracts structured data from URLs, the other maps a website's structure. There is no overlap in functionality.

Naming Consistency5/5

Both tool names are single imperative verbs ('extract' and 'map'), following a consistent and concise naming pattern.

Tool Count3/5

With only 2 tools, the server is on the lower end of acceptable scope. It covers basic functionality but feels minimal for a web crawling service.

Completeness3/5

The server provides core data extraction and site mapping, but lacks advanced features like recursive crawling or search, which are notable gaps for the domain.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Firecrawl Server

    codyde
    F
    license
    D
    quality
    D
    maintenance
    A server that provides tools to scrape websites and extract structured data from them using Firecrawl's APIs, supporting both basic website scraping in multiple formats and custom schema-based data extraction.
    2
    3
    -

  • Firecrawl MCP Server

    ampcome-mcps
    A
    license
    A
    quality
    D
    maintenance
    A Model Context Protocol server that enables web scraping, crawling, and content extraction capabilities through integration with Firecrawl.
    8
    117,089 npm
    2
    MIT

Appeared in Searches