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:
@@ -30,8 +30,7 @@ Add to your `claude_desktop_config.json`:
|
||||
{
|
||||
"mcpServers": {
|
||||
"gemini": {
|
||||
"command": "python",
|
||||
"args": ["/absolute/path/to/gemini-mcp-server/server.py"],
|
||||
"command": "/absolute/path/to/gemini-mcp-server/run_gemini.sh",
|
||||
"env": {
|
||||
"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
|
||||
|
||||
### 4. Connect to Claude Code
|
||||
|
||||
Reference in New Issue
Block a user