"laya" matching MCP servers:

Enables coding agents to make confident decisions using calibrated probabilistic tools for screening, verification, ranking, classification, and gating, fully self-hosted as an optional MCP server.

Enables clients to submit typed System One decisions against the Laya model and check service readiness over stdio or HTTP SSE, with the same configuration, validation, and API-key protection as the REST API.

Enables AI agents to run local, CPU-only inference for decision tasks such as choosing among labels, estimating yes/no probability, and scoring ordered descriptions. Exposes these capabilities through MCP tools, REST/Swagger endpoints, and a browser test console without GPUs, paid APIs, or databases.

Enables MCP clients to evaluate typed choice, score, and noul questions and list available models on configured backends such as Ollama nimble/tev/clef, TypeSafe jev, Kev, or Laya via two stdio tools.

Enables OpenAI-compatible clients to send llama-server only the MCP tools relevant to each request, reducing prompt size and cold prefill latency through pluggable selectors such as Laya or BM25 while preserving normal tool calling.

Enables Claude Code and other MCP clients to obtain fast, low-latency snap decisions — tool choice, option selection, and abstention when confidence is low — from a pluggable local decision engine such as Laya, Von, an Ollama chat model, or a custom provider. Engines can be swapped without changing the stable tools the client sees, with validation, per-attempt timeouts, confidence thresholds, and fallback chains handled by the server.

Checks what local coding agents such as Claude Code, Codex and Cursor really did: files changed, commands run and test results read from test output, not the agent's word. Unclear test results can be double-checked by Laya (on your computer) or TypeSafe's Jev (cloud, your own API key). Read-only.

Enables Claude Code and Codex Herdr workers to get local, advisory routing decisions by selecting a client, model, effort tier, and worker launch instruction for a stage, and by ranking a short list of bounded next actions. Decisions come from a selectable local backend (Laya or a local Kev model), returning confidence and uncertainty without executing anything or granting permissions.

An MCP server that enforces safe git commits by allowing only specified files and providing fixup capabilities for earlier commits.

A local Model Context Protocol server for controlling Autodesk Maya, providing typed tools for scene, modeling, animation, and more without Maya imports in the server process.

A design-intelligent MCP server for Figma with 201 tools and built-in design rules, works with Cursor and Claude Code.

Provides a deterministic MCP server that orchestrates projects across web, backend, games, AI, payments, fiscal, and infrastructure domains, with safe file writing, audit logging, and framework-aware context routing.

Enables users to list, search, and read official versioned PostgreSQL documentation, including archived, beta, and development releases, and retrieve pages as Markdown.

Model Context Protocol (MCP) server implementation for Autodesk Maya

Enables AI assistants to connect to and control Autodesk Maya for 3D modeling, animation, and rendering operations through the Model Context Protocol, supporting object creation, transformation, scene queries, and Python command execution.

Enables agents to query LAVA board farms, submit and manage test jobs, and open interactive board sessions via the LAVA REST API.

Enables AI assistants to programmatically control Autodesk Maya via natural language using over 30 tools for 3D modeling, lighting, and animation. It connects through Maya's command port to facilitate procedural scene generation and complex production-ready workflows.