/ 目录 / 演练场 / GPT Researcher
● 官方 assafelovic 🔑 需要你的密钥

GPT Researcher

作者 assafelovic · assafelovic/gpt-researcher

Autonomous research agent: give it a question, it plans searches, reads sources, and writes a cited report — callable from Claude via MCP.

GPT Researcher decomposes a research question into sub-queries, fetches web and document sources, and synthesizes a cited report. Its MCP server lets Claude offload deep research while staying in the chat.

为什么要用

核心特性

实时演示

实际使用效果

就绪

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": {
    "gpt-researcher-mcp": {
      "command": "uvx",
      "args": [
        "gpt-researcher-mcp"
      ]
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "gpt-researcher-mcp": {
      "command": "uvx",
      "args": [
        "gpt-researcher-mcp"
      ]
    }
  }
}

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": {
    "gpt-researcher-mcp": {
      "command": "uvx",
      "args": [
        "gpt-researcher-mcp"
      ]
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "gpt-researcher-mcp": {
      "command": "uvx",
      "args": [
        "gpt-researcher-mcp"
      ]
    }
  }
}

格式与 Claude Desktop 相同。重启 Windsurf 生效。

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "gpt-researcher-mcp",
      "command": "uvx",
      "args": [
        "gpt-researcher-mcp"
      ]
    }
  ]
}

Continue 使用服务器对象数组,而非映射。

~/.config/zed/settings.json
{
  "context_servers": {
    "gpt-researcher-mcp": {
      "command": {
        "path": "uvx",
        "args": [
          "gpt-researcher-mcp"
        ]
      }
    }
  }
}

加入 context_servers。Zed 保存后热重载。

claude mcp add gpt-researcher-mcp -- uvx gpt-researcher-mcp

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: GPT Researcher

Run a deep research task from inside Claude

👤 Developers ⏱ ~15 min intermediate

何时使用: Question needs 20+ sources and a written summary, not 3 web hits.

步骤
  1. Bridge
    Add GPT Researcher MCP.✓ 已复制
    → Tool visible
  2. Commission
    Ask Claude to commission the research.✓ 已复制
    → Researcher runs
  3. Receive
    Cited report comes back.✓ 已复制
    → Ready to use

结果: Cited multi-source report in one prompt.

组合

与其他 MCP 搭配,撬动十倍杠杆

gpt-researcher-mcp + exa-mcp-server

Use Exa for fast lookups; GPT Researcher for deep multi-source work

Combine gpt-researcher-mcp with exa-mcp-server: Use Exa for fast lookups; GPT Researcher for deep multi-source work✓ 已复制

工具

此 MCP 暴露的能力

工具输入参数何时调用成本
research.run (see docs) Run a multi-step research task 1 call
research.status (see docs) Check on a running task 1 call

成本与限制

运行它的成本

API 配额
Per LLM + search provider
每次调用 Token 数
Heavy — long contexts
费用
Free OSS; LLM + search costs
提示
Set max-iterations to cap runaway researchers

安全

权限、密钥、影响范围

最小权限: search:read
凭据存储: API keys in env
数据出站: Configured providers
切勿授予: Send proprietary data unless self-hosting

故障排查

常见错误与修复

Researcher loops on same sources

Lower iteration cap; tighten the question

替代方案

GPT Researcher 对比其他方案

替代方案何时用它替代权衡
Manual web + search MCPOne-off questionsNo synthesis layer

更多

资源

📖 阅读 GitHub 上的官方 README

🐙 查看未解决的 issue

🔍 浏览全部 400+ MCP 服务器和 Skills