Firecrawl CLI Skill

Name: Firecrawl CLI Skill (Claude Skill)
Author: firecrawl

为什么要用

核心特性

CLI and Agent Skill for Firecrawl - add scrape, search, and browsing capabilities to AI agents.
Maintained by firecrawl (official)
Written in TypeScript
419+ GitHub stars at last check
Open source on GitHub

实时演示

实际使用效果

firecrawl-cli-skill.replay ▶ 就绪

0/0

安装

选择你的客户端

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "firecrawl-cli-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/firecrawl/cli",
        "~/.claude/skills/firecrawl-cli-skill"
      ],
      "_inferred": true
    }
  }
}

打开 Claude Desktop → Settings → Developer → Edit Config。保存后重启应用。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "firecrawl-cli-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/firecrawl/cli",
        "~/.claude/skills/firecrawl-cli-skill"
      ],
      "_inferred": true
    }
  }
}

Cursor 使用与 Claude Desktop 相同的 mcpServers 格式。项目级配置优先于全局。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "firecrawl-cli-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/firecrawl/cli",
        "~/.claude/skills/firecrawl-cli-skill"
      ],
      "_inferred": true
    }
  }
}

点击 Cline 侧栏中的 MCP Servers 图标，然后选 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "firecrawl-cli-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/firecrawl/cli",
        "~/.claude/skills/firecrawl-cli-skill"
      ],
      "_inferred": true
    }
  }
}

格式与 Claude Desktop 相同。重启 Windsurf 生效。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "firecrawl-cli-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/firecrawl/cli",
        "~/.claude/skills/firecrawl-cli-skill"
      ]
    }
  ]
}

Continue 使用服务器对象数组，而非映射。

~/.config/zed/settings.json

{
  "context_servers": {
    "firecrawl-cli-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/firecrawl/cli",
          "~/.claude/skills/firecrawl-cli-skill"
        ]
      }
    }
  }
}

加入 context_servers。Zed 保存后热重载。

claude mcp add firecrawl-cli-skill -- git clone https://github.com/firecrawl/cli ~/.claude/skills/firecrawl-cli-skill

一行命令搞定。用 claude mcp list 验证，claude mcp remove 卸载。

使用场景

实战用法： Firecrawl CLI Skill

Use Firecrawl CLI Skill for its primary workflow

👤 Developers using AI coding agents ⏱ ~10 min beginner

何时使用： You need the capability: CLI and Agent Skill for Firecrawl - add scrape, search, and browsing capabilities to AI agents.

前置条件

Skill installed — git clone https://github.com/firecrawl/cli ~/.claude/skills/firecrawl-cli-skill

步骤

Install

Install Firecrawl CLI Skill following the README at https://github.com/firecrawl/cli✓ 已复制

→ Skill appears in your client's available tools/skills
Invoke

Use Firecrawl CLI Skill to complete the task described in its docs.✓ 已复制

→ Agent calls the relevant tool/skill and returns a result

结果： Working integration with the capabilities advertised by the project.

注意事项

README is the source of truth; details here may lag upstream — Check https://github.com/firecrawl/cli for the latest setup steps and tool list