# Example MCP Configuration for Clockify Server
## For Claude Desktop
### macOS
Edit: `~/Library/Application Support/Claude/claude_desktop_config.json`
### Windows
Edit: `%APPDATA%\Claude\claude_desktop_config.json`
### Linux
Edit: `~/.config/Claude/claude_desktop_config.json`
```json
{
"mcpServers": {
"clockify": {
"command": "uvx",
"args": ["clockify-mcp-server"],
"env": {
"CLOCKIFY_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
```
## For Development (Local Installation)
```json
{
"mcpServers": {
"clockify": {
"command": "python",
"args": ["-m", "clockify_mcp.server"],
"cwd": "/path/to/clockify-mcp-server",
"env": {
"CLOCKIFY_API_KEY": "YOUR_API_KEY_HERE",
"PYTHONPATH": "/path/to/clockify-mcp-server/src"
}
}
}
}
```
## Getting Your API Key
1. Log in to [Clockify](https://clockify.me/)
2. Go to [User Settings](https://clockify.me/user/settings)
3. Scroll to the "API" section
4. Click "Generate" to create a new API key
5. Copy the key and use it in your configuration
## Environment Variables
You can also set the API key as an environment variable:
```bash
# Add to ~/.bashrc, ~/.zshrc, or equivalent
export CLOCKIFY_API_KEY="your_api_key_here"
```
## Testing Your Configuration
After configuring, restart your MCP client (e.g., Claude Desktop) and try:
```
"Find all time entries for [your name] from the last week"
```
If configured correctly, Claude will be able to access your Clockify data.
## Troubleshooting
### Server Not Starting
- Check that `uvx` or `python` is in your PATH
- Verify the API key is set correctly
- Check logs in your MCP client
### "No workspaces found"
- Verify your API key is valid
- Ensure you have at least one workspace in Clockify
- Try logging in to Clockify web interface to confirm access
### Permission Errors
- Some operations require workspace admin permissions
- Check your role in the Clockify workspace settings
