swarm-orchestrator
by halilogia
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RUNS_DIR | No | Directory where run logs are saved (default: ./runs) | ./runs |
| PYTHONPATH | No | Filesystem path to the SwarmOrchestrator project root, used in the MCP server configuration example (optional; the server automatically adds its own root to sys.path). | |
| MAX_RETRIES | No | Maximum number of retry attempts (default: 3) | 3 |
| DEFAULT_MODEL | No | Default model to use for tasks (default: all) | all |
| SAVE_RUN_LOGS | No | Whether to save batch run logs (default: true) | true |
| FALLBACK_MODEL | No | Model to fall back to if the default model fails (default: ag/gemini-3.7-flash-medium) | ag/gemini-3.7-flash-medium |
| RETRY_DELAY_SECONDS | No | Base delay in seconds between retries (default: 2) | 2 |
| LOCAL_ROUTER_API_KEY | No | API key for the local router, if required. | |
| LOCAL_ROUTER_BASE_URL | No | Base URL for the local OpenAI-compatible router (default: http://localhost:20128/v1) | http://localhost:20128/v1 |
| MAX_CONCURRENT_WORKERS | No | Maximum number of concurrent workers (default: 8) | 8 |
| REQUEST_TIMEOUT_SECONDS | No | Base timeout in seconds for HTTP requests (default: 150) | 150 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues