io.github.dockndevai/mcp-laya MCP Server
io.github.dockndevai/mcp-laya
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.dockndevai/mcp-laya MCP server?
Safe-by-default MCP for Laya: fast, local, typed decisions (classify/score/yes-no), 100+ langs.
How to install io.github.dockndevai/mcp-laya
Copy-paste configuration for popular MCP clients.
LAYA_DEFAULT_MODELCheckpoint to use: auto (Router picks) | english | multilingual | typed-decisions.
LAYA_MODELSComma-separated allowlist of checkpoints that may load. Empty = all.
LAYA_ALLOW_DOWNLOADAllow the one-time Hugging Face checkpoint download. Off by default (offline).
LAYA_MIN_CONFIDENCEFlag answers below this calibrated confidence (0 = never flag).
LAYA_DEVICEInference device: auto | cpu | cuda.
{
"mcpServers": {
"mcp-laya": {
"command": "uvx",
"args": [
"mcp-laya"
],
"env": {
"LAYA_DEFAULT_MODEL": "<YOUR_LAYA_DEFAULT_MODEL>",
"LAYA_MODELS": "<YOUR_LAYA_MODELS>",
"LAYA_ALLOW_DOWNLOAD": "<YOUR_LAYA_ALLOW_DOWNLOAD>",
"LAYA_MIN_CONFIDENCE": "<YOUR_LAYA_MIN_CONFIDENCE>",
"LAYA_DEVICE": "<YOUR_LAYA_DEVICE>"
}
}
}
}Related MCP servers
Full macOS control — drive a Mac like a human: shell, AppleScript, files, and human-like GUI.

Observe & operate a Mac — files, processes, apps, shell, AppleScript, GUI — safe by default.

Oracle Cloud discovery + Terraform generation for AI agents — read-only, secret-safe.
Safe-by-default MCP for OpenShift / Kubernetes: projects, pods, logs, deployments, routes.

Outlook mail and OneDrive files via Microsoft Graph — read, search, send and organize.
Manage Percona PostgreSQL + PgBouncer on Kubernetes — safe-by-default access modes and guards.