How do I use codex-laya-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@codex-laya-mcp Run laya_decide on these options and give me scores and truth probabilities." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

codex-laya-mcp

Local, read-only Laya typed decisions for Codex over Model Context Protocol.

This project is intentionally not a replacement model for Codex. It exposes bounded classification, scoring, truth-probability, batch decision, and token-budget planning tools backed by laya-mlx on Apple Silicon.

Included tools

laya_plan: exact prompt-budget preflight without inference.
laya_decide: batched choice, score, and truth-probability decisions.
laya_classify, laya_score, and laya_check: focused convenience tools.

Every inference result includes the full distribution, uncertainty metrics, model metadata, and an advisory answer/review/abstain policy. Inputs that Laya would silently truncate are rejected.

Related MCP server: Jevbridge

Development

uv sync --extra dev
uv run ruff check .
uv run pytest
uv run codex-laya-mcp --help

The first real model call downloads the configured checkpoint unless it is already in the Hugging Face cache. Unit and MCP contract tests use a deterministic fake engine and do not download weights.

See CODEX_MCP_PROJECT_DESIGN.md for the complete design and docs/OPERATIONS.md for installation, Codex connection, and rollback.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

rtkcontext-mcp
com.clauxel.rtkcontext
A paid remote MCP for OpenAI Codex context compressor, built to return verdicts, receipts, usage log
AI & Machine Learning Monitoring
2
Quesen Deterministic Agent Decision Layer A
io.github.Shxnque
Deterministic decision layer for autonomous agents: reproducible PROCEED/REVIEW/SKIP verdicts.
Autonomous Agents Finance
52
Sophon Consulting A
consulting.sophon
Read-only, deterministic AI triage and readiness tools implementing Sophon's published rubrics.
AI & Machine Learning Testing & QA Tools
22
Reasoning Commons
io.github.chenyuan35
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
AI & Machine Learning Knowledge & Memory Autonomous Agents
2

Related MCP Servers

codebase-chat-mcp
Code Analysis Developer Tools
shinzarou-eng
A
license
Not graded
quality
F
maintenance
Enables local-first codebase intelligence, allowing chat, search, and audit operations on any repository with file:line citations, and supports offline deterministic modes without an LLM.
Updated 9 days ago (2026-09-14 20:45 UTC)
39 npm
2
MIT
Jevbridge
AI & Machine Learning Autonomous Agents Agent Orchestration
tacticocc
A
license
Not graded
quality
B
maintenance
Enables typed decisions, confidence-gated tool calls, and computer-use action selection for any LLM via Model Context Protocol, bridging TypeSafe Jev with Codex, Claude, Grok, and OpenCode.
Updated 3 days ago (2026-09-21 09:09 UTC)
40
MIT
laya-mcp
AI & Machine Learning Autonomous Agents
PerryLink
A
license
Not graded
quality
A
maintenance
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.
Updated 21 hours ago (2026-09-23 04:53 UTC)
Apache 2.0
laya-mcp
AI & Machine Learning Autonomous Agents
rdutra
A
license
A
quality
B
maintenance
Enables local bounded decision-making through MCP using a resident Core ML model, with tools for single decisions, batched decisions, and conservative context filtering.
Updated 2 days ago (2026-09-21 20:53 UTC)
4
2
Apache 2.0