model-mcp
by Windy-X211
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| port | No | Command-line port for the service. Set via --port. Default is 8765. | 8765 |
| transport | Yes | Command-line transport mode: stdio or http. Set via --transport. | |
| server.host | No | Listening address. Use 0.0.0.0 to expose to LAN. | 127.0.0.1 |
| server.port | No | Listening port. | 8765 |
| models[].name | No | Model name seen by client software. | agent-a |
| queue.lease_s | No | How long after A claims a request with no output before it is considered lost. | 120 |
| server.auth_token | No | When set, /v1/* requires Authorization: Bearer <token>. | |
| stream.heartbeat_s | No | SSE heartbeat interval in seconds. | 15 |
| queue.wait_timeout_s | No | Maximum single blocking wait for service_wait; must be less than MCP client timeout. | 40 |
| stream.replay_delay_ms | No | Replay delay in milliseconds when A provides full text at once. | 30 |
| queue.request_deadline_s | No | Total budget per request; returns 504 on timeout. | 600 |
| stream.replay_chunk_chars | No | Replay chunk size when A provides full text at once. | 24 |
| queue.reject_when_no_worker | No | When true, return 503 if no worker A is online. | true |
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 recent community issues