"laya" matching MCP servers:

Enables MiMo Desktop to run a typed-decision engine through local stdio MCP, returning choice/score/noul predictions with calibrated confidence for auto-execution, LLM review, or escalation—without generating text.

Provides an MCP interface to the Laya decision model, enabling typed queries (yes/no, multiple choice, score) with preflight token-budget reporting, honest confidence calibration, and structured error handling.

Enables local bounded decision-making through MCP using a resident Core ML model, with tools for single decisions, batched decisions, and conservative context filtering.

Provides fast, offline typed decision tools (classify, score, check, triage) to agents via the Model Context Protocol, enabling safe local inference across 100+ languages with calibrated confidence and no text generation.

Enables local, LLM-free probabilistic decisions (choice, classification, scoring, yes/no) with real probabilities in 100+ languages, as a drop-in replacement for jev-local tools.

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 coding agents to call Laya's decision-model presets as tools for tasks like request classification, guard checks, content moderation, ticket triage, and custom evaluations.

Enables typed decisions (yes/no, choice, score) with transparent preflight checks, honest confidence reporting, and health monitoring.

Enables MCP clients to run fast, local, non-autoregressive System-1 decisions on text, including classification, triage, routing, and safety gating, via six typed tools with probabilistic outputs.

Enables typed decisions (choice/score/noul) from Laya-MLX over MCP on Apple Silicon, without text generation.

Enables local Laya-MLX typed decisions (classification, scoring, risk routing, and yes/no) for coding agents like Codex, Claude Code, DeepSeek Harness, and Pi via MCP, running entirely on Apple Silicon Macs.

Enables fully offline, token-free screening of text through a local Laya typed-decision model, exposing prompt-injection/jailbreak detection plus structured choice, score, and yes/no judgments in about 55ms per call. It also reports service status with measured metrics and known limitations.

Enables local, read-only Laya typed decisions for Codex, providing classification, scoring, truth-probability, batch decision, and token-budget planning tools on Apple Silicon.

Enables AI assistants to control a web browser through Playwright-compatible tools, with an on-device decision engine for autonomous task completion and optional LLM escalation.

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 local MCP clients to answer questions about the current browser page by capturing DOM context, routing them to fast or deep OpenAI models via a local model router, and optionally filling forms and submitting answers.

An MCP server that brings a local MLX-powered decision layer to coding agents, letting them choose short workflow actions such as task routing, risk checks, next steps, and test/review decisions without cloud APIs.

Enables local, token-free typed decisions (choice/bool/score) in milliseconds for oh-my-pi sessions, with per-request language routing and confidence-based escalation.

Laya-MLX as an MCP server (and plain-HTTP API). It answers typed decisions — choose an option / score a rubric / is this true? — on your own machine (Apple Silicon / MLX), with no cloud and ~10ms after warm-up. Not a chatbot. No token-by-token text, no JSON that can break. One forward pass returns a structured answer you can branch on. Ideal for routing, triage, classification, lead scoring, and g

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.