Gemini Research

Provides real-time web research for Claude Desktop using Gemini 2.5 Flash with native Google Search grounding.

python

9

GitHub Stars

python

Language

3 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "claudiusbotticus-gemini-research-mcp": {
      "command": "python",
      "args": [
        "C:\\path\\to\\gemini-research-mcp\\server.py"
      ]
    }
  }
}

This MCP server adds real-time web research capabilities to Claude Desktop by running Gemini 2.5 Flash with native Google Search grounding, letting you perform topic research or summarize any web page directly from your MCP client.

How to use

Once the server is running, you can access two tools from your MCP client:

research: Enter a topic or question to have Gemini search the web and return a factual summary. Use this for current events, recent news, or topics beyond Claude's built-in knowledge.
research_url: Enter a URL to have Gemini fetch and summarize the page content. Both tools support a detail parameter with three levels: low (~500 words), normal (~1500 words), or high (~3000 words). When you select a level, Gemini will tailor the depth of the summary accordingly.

How to install

Prerequisites: you need Python installed on your system and a Google AI Studio API key. The server reads the API key from a local environment file created during setup.

Step 1: Install dependencies

pip install -r requirements.txt


Step 2: Run the setup GUI to input your API key
```python setup.py````A small window will appear. Paste your API key and click Save. Your key is stored in a local .env file and never leaves your machine.```

Step 3: Start the MCP server
```python server.py````The server starts and awaits connections from your MCP client. The API key is read from the local .env file created during setup.```

Step 4: Connect to Claude Desktop
Open Claude Desktop config and add the MCP configuration shown below, then restart Claude Desktop to enable the connection.

## Configuration and usage notes

The server stores your API key in a local .env file created by the setup GUI. Do not commit this file to version control. The MCP entry you add to Claude Desktop points to the local Python process that runs server.py.

Example MCP connection shown in Claude Desktop config (local stdio mode):

{ "gemini-research": { "command": "python", "args": ["C:\path\to\gemini-research-mcp\server.py"] } }


## Available tools

### research

Accepts a topic or question, performs web searches via Gemini, and returns a factual, synthesized summary with adjustable detail levels.

### research\_url

Accepts a URL, fetches the page content, and returns a summarized analysis of the page with adjustable detail levels.