Configuration & Settings
Fine-tune the behavior and performance of your MCP Server.
Global Settings
Section titled “Global Settings”Navigate to MCP Server → Configuration → Settings to manage these parameters:
| Setting | Default | Description |
|---|---|---|
| Enable MCP Server | ✅ | Master on/off switch for the server |
| Log Requests | ✅ | Enable full request/response audit logging |
| Global Rate Limit | 0 (unlimited) | Global requests/minute across all keys (0 = no limit) |
| GET Rate Limit | 0 (inherit global) | Optional method-specific GET requests/minute |
| POST Rate Limit | 0 (inherit global) | Optional method-specific POST requests/minute |
| Max Payload Size | 1,048,576 (1 MB) | Maximum POST body size in bytes |
| Max Batch Size | 50 | Maximum JSON-RPC batch item count |
| Session Timeout | 3600s (1 hr) | Idle session timeout in seconds |
| Max Active Sessions | 500 | Maximum simultaneously active SSE sessions |
| Session Queue Size | 100 | Maximum queued responses per session |
| Max Log Age | 30 days | Auto-delete logs older than this threshold |
| Max Log Entry Size | 65,536 (64 KB) | Max size of a single log entry before truncation |
| CORS Allowed Origins | (empty) | Comma-separated list of allowed domain origins |
| Blocked Models | (empty) | Comma-separated extra model names to block from MCP access |
| Server Instructions | (Default prompt) | The “brain” of the server. This massive prompt is sent to the AI to teach it how to use Odoo tools and map business terms. |
Audit Logging
Section titled “Audit Logging”The MCP Server provides comprehensive traceability for all AI interactions.
Accessing Logs
Section titled “Accessing Logs”- Go to MCP Server → Audit → Request Logs.
- View timestamp, API key, endpoint called, request/response data, and error messages.
- Filter by date range, model, or API key for investigation.
Performance Considerations
Section titled “Performance Considerations”- Logging full request/response payloads can consume significant database space.
- Use Max Log Entry Size to truncate large payloads.
- Use Max Log Age to ensure automatic cleanup of old data.
Best Practices
Section titled “Best Practices”- Batching: Each API call counts against rate limits; use JSON-RPC batches for related operations.
- Filtering: Use
searchwith specific domains and fields to minimize payload size and processing time. - Sessions: Monitor session counts via the
/mcp/healthendpoint to detect potential resource leaks in custom agents.