MCP Server for Laya
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LAYA_PRELOAD | No | Load the model at startup instead of on the first call. | false |
| MCP_HTTP_HOST | No | HTTP server bind address. Only used when MCP_TRANSPORT=http. | 0.0.0.0 |
| MCP_HTTP_PORT | No | HTTP server port. Only used when MCP_TRANSPORT=http. | 3005 |
| MCP_TRANSPORT | No | Transport mode: 'stdio' for npx/Claude Desktop/VS Code, or 'http' for Streamable HTTP/Docker/remote clients. | stdio |
| LAYA_MODEL_DIR | Yes | Directory containing the ONNX export (encoder.onnx, head.onnx, tokenizer.json, etc.). Validated at startup. | |
| LAYA_NUM_THREADS | No | ONNX Runtime CPU threads. Defaults to the runtime default. |
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