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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.