laya-mcp
by andragon3110
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LAYA_URL | No | Where the Python server listens | http://127.0.0.1:8765 |
| LAYA_HOST | No | Bind address for the Python server | 127.0.0.1 |
| LAYA_PORT | No | Bind port for the Python server | 8765 |
| LAYA_DEVICE | No | Device for Laya: auto / cpu / cuda | auto |
| LAYA_PRELOAD | No | Load all 3 checkpoints at startup | 1 |
| LAYA_LOG_LEVEL | No | uvicorn log level | WARNING |
| LAYA_MAX_LOADED | No | Max resident checkpoints (LRU eviction) | 3 |
| LAYA_TIMEOUT_MS | No | Per-call HTTP timeout from MCP to Python | 5000 |
| LAYA_TOOL_TIMEOUT_MS | No | Per-tool MCP timeout | 8000 |
| LAYA_STANDALONE_REPOS | No | Use per-checkpoint repos instead of the hub repo | 0 |
| LAYA_HEALTH_INTERVAL_MS | No | Background watcher poll interval | 10000 |
| LAYA_AUTO_TASK_DETECTION | No | Auto-route to typed-decisions on workflow match | 1 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
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 | |
Maintenance
ActivityMaintained
ResponsivenessNo issues