Gemini Research MCP
Provides real-time web research and URL summarization capabilities using Gemini 2.5 Flash with native Google Search grounding. It enables users to perform factual searches and summarize web content directly within MCP-compatible clients like Claude Desktop.
README
gemini-research-mcp
An MCP server that adds real-time web research to Claude Desktop (and any other MCP client). Powered by Gemini 2.5 Flash with native Google Search grounding. Free to use — no credit card required, just a Google AI Studio API key.
Built by a Claude instance. Yes, an AI made this tool to make itself more capable.
What it does
Adds two tools to Claude Desktop:
research— Give it any topic or question. Gemini searches the web and returns a factual summary. Great for current events, recent news, anything past Claude's knowledge cutoff.research_url— Give it a URL. Gemini fetches and summarizes the page.
Both support a detail parameter: low (~500 words), normal (~1500 words), or high (~3000 words).
Setup
1. Get a free Gemini API key
Go to aistudio.google.com/apikey and create a key. It's free — no billing required.
2. Install dependencies
pip install -r requirements.txt
3. Run setup.py
python setup.py
A small window will appear. Paste your API key and click Save. That's it — your key is stored in a local .env file and never leaves your machine.

4. Add to Claude Desktop config
Open %APPDATA%\Claude\claude_desktop_config.json and add:
"gemini-research": {
"command": "python",
"args": ["C:\\path\\to\\gemini-research-mcp\\server.py"]
}
Replace the path with wherever you cloned this repo. Restart Claude Desktop.
Why Gemini specifically?
Gemini 2.5 Flash has native Google Search grounding — it can search the web as part of its generation, not as a separate step. This means the summary is coherent and synthesized rather than just a list of search results. It's also fast and the free tier is generous enough for daily Claude use.
Files
| File | Purpose |
|---|---|
server.py |
The MCP server |
setup.py |
GUI for entering your API key |
requirements.txt |
Python dependencies |
.env |
Your API key (created by setup.py, gitignored) |
.gitignore note
The .env file containing your key is automatically excluded from git. Never commit it.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。