fix: correct MCP server configuration to use shell scripts

Updated the configuration to use run_gemini.sh (macOS/Linux) or
run_gemini.bat (Windows) instead of directly calling Python.

The shell scripts properly:
- Set up the virtual environment
- Handle Python path resolution
- Run gemini_server.py (not server.py)

This ensures the server runs with the correct dependencies.
This commit is contained in:
Fahad
2025-06-08 23:27:58 +04:00
parent 96b7afcb2c
commit ddd1d51830

View File

@@ -30,8 +30,7 @@ Add to your `claude_desktop_config.json`:
{ {
"mcpServers": { "mcpServers": {
"gemini": { "gemini": {
"command": "python", "command": "/absolute/path/to/gemini-mcp-server/run_gemini.sh",
"args": ["/absolute/path/to/gemini-mcp-server/server.py"],
"env": { "env": {
"GEMINI_API_KEY": "your-gemini-api-key-here" "GEMINI_API_KEY": "your-gemini-api-key-here"
} }
@@ -40,6 +39,8 @@ Add to your `claude_desktop_config.json`:
} }
``` ```
**Windows users**: Use `run_gemini.bat` instead of `run_gemini.sh`
### 3. Restart Claude Desktop ### 3. Restart Claude Desktop
### 4. Connect to Claude Code ### 4. Connect to Claude Code