快速接入

先看主来源和安装命令，再打开仓库或文档；下面只保留这个条目的关键接入事实。

命令预览

npx @bharatvansh/gemini-deep-research-mcp

详细介绍

Gemini深度研究MCP

](https://pypi.org/project/gemini-deep-research-mcp/) ](https://www.npmjs.com/package/@bharatvansh/gemini-deep-research-mcp) ![License: MIT](https://opensource.org/licenses/MIT)

暴露Gemini的MCP服务器 深度研究代理 用于全面的网络研究。

一键安装

IDE	安装
光标	![Install in Cursor](https://cursor.com/en/install-mcp?name=gemini-deep-research&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJnZW1pbmktZGVlcC1yZXNlYXJjaC1tY3AiXSwiZW52Ijp7IkdFTUlOSV9BUElfS0VZIjoieW91ci1hcGkta2V5In19)
VS Code	![Install in VS Code](https://insiders.vscode.dev/redirect/mcp/install?name=gemini-deep-research&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22gemini-deep-research-mcp%22%5D%2C%22env%22%3A%7B%22GEMINI_API_KEY%22%3A%22your-api-key%22%7D%7D)
VS代码内部人员	![Install in VS Code Insiders](https://insiders.vscode.dev/redirect/mcp/install?name=gemini-deep-research&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22gemini-deep-research-mcp%22%5D%2C%22env%22%3A%7B%22GEMINI_API_KEY%22%3A%22your-api-key%22%7D%7D&quality=insiders)

注：单击后，替换 your-api-key 和你一起 Gemini API密钥.VS Code需要1.101+版本。

______________________________________________________________________

安装方法

使用npx（Node.js）

需要 16+和紫外线.

npx @bharatvansh/gemini-deep-research-mcp

VS Code config

{
  "servers": {
    "gemini-deep-research": {
      "command": "npx",
      "args": ["-y", "@bharatvansh/gemini-deep-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Desktop config

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "npx",
      "args": ["-y", "@bharatvansh/gemini-deep-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Windsurf config

添加到 ~/.codeium/windsurf/mcp_config.json （macOS/Linux）或 %USERPROFILE%\.codeium\windsurf\mcp_config.json （Windows）：

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "npx",
      "args": ["-y", "@bharatvansh/gemini-deep-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Cline config

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "npx",
      "args": ["-y", "@bharatvansh/gemini-deep-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Code config

添加到 ~/.claude/settings.json:

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "npx",
      "args": ["-y", "@bharatvansh/gemini-deep-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Codex config

添加到 ~/.codex/config.toml:

[mcp_servers.gemini-deep-research]
command = "npx"
args = ["-y", "@bharatvansh/gemini-deep-research-mcp"]

[mcp_servers.gemini-deep-research.env]
GEMINI_API_KEY = "your-api-key"

Cursor config

添加到 ~/.cursor/mcp.json:

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "npx",
      "args": ["-y", "@bharatvansh/gemini-deep-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Antigravity config

加入你的反重力 mcp_config.json:

{
  "gemini-deep-research": {
    "command": "npx",
    "args": ["-y", "@bharatvansh/gemini-deep-research-mcp"],
    "env": {
      "GEMINI_API_KEY": "your-api-key"
    }
  }
}

______________________________________________________________________

使用uvx（Python）

需要紫外线.

uvx gemini-deep-research-mcp

VS Code config

{
  "servers": {
    "gemini-deep-research": {
      "command": "uvx",
      "args": ["gemini-deep-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Desktop config

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "uvx",
      "args": ["gemini-deep-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Windsurf config

添加到 ~/.codeium/windsurf/mcp_config.json （macOS/Linux）或 %USERPROFILE%\.codeium\windsurf\mcp_config.json （Windows）：

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "uvx",
      "args": ["gemini-deep-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Cline config

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "uvx",
      "args": ["gemini-deep-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Code config

添加到 ~/.claude/settings.json:

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "uvx",
      "args": ["gemini-deep-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Codex config

添加到 ~/.codex/config.toml:

[mcp_servers.gemini-deep-research]
command = "uvx"
args = ["gemini-deep-research-mcp"]

[mcp_servers.gemini-deep-research.env]
GEMINI_API_KEY = "your-api-key"

Cursor config

添加到 ~/.cursor/mcp.json:

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "uvx",
      "args": ["gemini-deep-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Antigravity config

加入你的反重力 mcp_config.json:

{
  "gemini-deep-research": {
    "command": "uvx",
    "args": ["gemini-deep-research-mcp"],
    "env": {
      "GEMINI_API_KEY": "your-api-key"
    }
  }
}

______________________________________________________________________

使用pip

pip install gemini-deep-research-mcp

VS Code config

{
  "servers": {
    "gemini-deep-research": {
      "command": "gemini-deep-research-mcp",
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Desktop config

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "gemini-deep-research-mcp",
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Windsurf config

添加到 ~/.codeium/windsurf/mcp_config.json （macOS/Linux）或 %USERPROFILE%\.codeium\windsurf\mcp_config.json （Windows）：

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "gemini-deep-research-mcp",
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Cline config

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "gemini-deep-research-mcp",
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Code config

添加到 ~/.claude/settings.json:

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "gemini-deep-research-mcp",
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Codex config

添加到 ~/.codex/config.toml:

[mcp_servers.gemini-deep-research]
command = "gemini-deep-research-mcp"

[mcp_servers.gemini-deep-research.env]
GEMINI_API_KEY = "your-api-key"

Cursor config

添加到 ~/.cursor/mcp.json:

{
  "mcpServers": {
    "gemini-deep-research": {
      "command": "gemini-deep-research-mcp",
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Antigravity config

加入你的反重力 mcp_config.json:

{
  "gemini-deep-research": {
    "command": "gemini-deep-research-mcp",
    "env": {
      "GEMINI_API_KEY": "your-api-key"
    }
  }
}

______________________________________________________________________

反重力

打开 代理侧面板 → click ... → MCP商店
搜索您的MCP服务器或单击 添加自定义服务器
将此配置添加到您的 mcp_config.json:

{
  "gemini-deep-research": {
    "command": "uvx",
    "args": ["gemini-deep-research-mcp"],
    "env": {
      "GEMINI_API_KEY": "your-api-key"
    }
  }
}

______________________________________________________________________

先决条件

Install uv (required for npx/uvx methods)

# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

______________________________________________________________________

工具： `gemini_deep_research`

使用Gemini的Deep research Agent进行全面的网络研究。直到研究完成（通常为10-20分钟）。

何时使用：

需要多源分析的复杂主题
来自网络的综合信息
事实核查和交叉引用

参数	类型	必填	默认	说明
`prompt`	string	✓	—	您的研究问题或主题
`include_citations`	boolean		`true`	包含已解析的源URL

输出	描述
`status`	`completed`, `failed`，或 `cancelled`
`report_text`	综合研究报告

配置

变量	必填	默认	描述
`GEMINI_API_KEY`	✓	—	Your Gemini API密钥
`GEMINI_DEEP_RESEARCH_AGENT`		`deep-research-pro-preview-12-2025`	要使用的模型

发展

git clone https://github.com/bharatvansh/gemini-deep-research-mcp.git
cd gemini-deep-research-mcp
pip install -e .[dev]
pytest

许可证

麻省理工学院

目录标签

数据分析PythonVS Code信息检索网络研究本地部署自动化研究GeminiAPI

支持客户端

Claude DesktopClaudeCursorWindsurfClineVS CodeVS Code Insiders

接入字段

传输方式（transport，传输协议）

stdio

鉴权方式（authType，认证方式）

none

运行时（runtime，运行环境）

Node.js

来源包（packageName，安装包名）

@bharatvansh/gemini-deep-research-mcp

工具数量（toolCount，工具数）

1

资源数量（resourceCount，资源数）

0

提示词数量（promptCount，提示词数）

0

权限和风险

stdionone部署方式未说明

接入前请确认传输方式、认证方式和部署位置，并根据实际工具能力限制访问范围。

安装前确认

不要直接授予不必要的文件、网络或账号权限；先核对安装命令和配置内容。

来源信息

MCP World

mcpworld.com

/detail/d14aec3b0687f14ab39c6e13520e64b9

一个提供Gemini深度研究代理功能的MCP服务器，用于全面的网络研究。

继续浏览同类 MCP

更多数据服务 MCP（6,870）返回 MCP 目录

上一个 MCP

Gemini Data Analysis Research MCP Server

全面解析Gemini Data Analysis Research MCP ServerMCP Server的核心功能、安装配置和实用案例。作为顶级Model Context Protocol服务器，Gemini Data Analysis Research MCP Server能让AI助手访问实时数据、执行操作，为您提供更智能的工作体验和自动化解决方案。

下一个 MCP

Gemini Embedding 2 MCP Server

基于Gemini Embedding 2的多模态本地内存MCP服务器，为AI代理提供统一的跨模态搜索和本地持久化存储。

Gemini Deep Research MCP

快速接入

详细介绍

Gemini深度研究MCP

一键安装

安装方法

使用npx（Node.js）

使用uvx（Python）

使用pip

反重力

先决条件

工具： gemini_deep_research

配置

发展

许可证

目录标签

接入字段

权限和风险

来源信息

继续浏览同类 MCP

工具： `gemini_deep_research`