MCPLaya
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
MCPLaya
A local, agent-independent stdio MCP server for delegating structured choices to Laya: text categorization, independent tags, ordinal ratings, statement probabilities and bounded action selection. For dependent decisions, use observe → ask Laya → execute one action with the agent → record real outcome → observe again. It never executes actions itself.
Created independently alongside LayaTUI-MCP; no TUI or upstream server monkey-patching. Laya 0.3.20 is installed from PyPI; model weights are not included.
Install and connect
Download and extract the repository, or clone it. From its directory, run these commands in PowerShell, Terminal or a Linux shell with uv installed:
uv tool install --python 3.12 .
mcplaya doctor
mcplaya configuv can install Python 3.12 automatically. If mcplaya is not on PATH, run
uv tool update-shell and reopen the terminal. The installed server runs outside
the repository and needs no Git, Docker, Node.js, administrator access or API key
at runtime. Python 3.10–3.12 is the supported package range.
Paste the output of mcplaya config into a client using mcpServers. It contains
the installed Python's absolute path and arguments, avoiding shell and PATH
differences. Merge the entry with existing configuration. Other supported formats:
mcplaya config --format vscode
mcplaya config --format opencode
mcplaya config --format opencode-v1VS Code uses .vscode/mcp.json; OpenCode v2 uses mcp.servers, while v1 uses
mcp directly. For other agents, configure the executable and arguments from
the generated JSON in their MCP UI. Configuration commands only print text.
The agent launches mcplaya serve as a local subprocess; mcplaya without
arguments remains equivalent. No network listener is started.
The target platforms are Windows x64, Linux x64/ARM64, and macOS Apple Silicon and Intel, subject to native dependency and OS requirements. CPU is the default; CUDA or Apple MPS acceleration is optional. First inference downloads checkpoint files and can take time; installation and models can require several GB of disk space. Startup, status, configuration and diagnostics do not download weights.
Compatibility requires an agent that can launch local stdio MCP servers. An agent without MCP support, or a remote-only client, needs its own adapter. There is no claim of compatibility with every OS, hardware configuration or agent. See installation and compatibility for offline use, manual installation, storage paths and validation limits. See the tool reference for request examples and the decision workflow for agent integration guidance.
Related MCP server: ratchet-mcp
Tools and behavior
Tool | Purpose |
| Lazy model/device report |
| Independent choice, ordered score and P(true) questions |
| One bounded choice among 2-20 concrete candidates |
| Goal, step budget, confidence threshold, model |
| Fresh observation and candidates → one pending decision |
| Record observed succeeded/failed/skipped outcome |
| Recover durable state and current revision |
| Finish with a reason supported by evidence |
SQLite stores caller-supplied observations and history across restarts. Revision
checks prevent stale updates; one pending decision prevents jumping ahead.
Three consecutive failures block the loop. Skipped proposals consume budget too.
Low or missing confidence returns requires_review: true and no automatic
recommendation. Confidence is not authorization or a correctness guarantee.
Callers must review real-world permissions and verify action results themselves.
General checkpoints have not been validated for arbitrary action selection.
Evaluate on your domain; a compatible LAYA_ACTION_MODEL local checkpoint can
replace the router for all inference tools, including laya_predict.
Its supported schemas, license and accuracy are the deployer's responsibility.
The tool sends a short current observation plus five recent outcomes; long
inputs may exceed or be truncated by the checkpoint's context window.
Settings: LAYA_DEVICE (torch device), LAYA_ACTION_MODEL (checkpoint path),
MCPLAYA_DB (SQLite path). Default DB: %LOCALAPPDATA%/mcplaya/sequences.sqlite3
on Windows, ~/Library/Application Support/mcplaya/sequences.sqlite3 on macOS,
and $XDG_STATE_HOME/mcplaya/sequences.sqlite3 or
~/.local/state/mcplaya/sequences.sqlite3 on Linux. Existing legacy databases
remain in use when no database exists at the native location. History is local plaintext; it
contains only what the caller supplies. Users can remove the DB to erase all
history while the server is stopped. No telemetry or paid API dependency.
Agent usage skill
skills/mcplaya-decisions/SKILL.md teaches an agent how to use the connected MCP. It covers text classification, intent and email routing, independent tags, urgency and sentiment, screening signals, retrieval relevance, specialist workflows and bounded action sequences.
The skill includes a researched use-case catalog, request recipes and performance/model guidance. It explains how to reuse warm models, combine independent questions and handle uncertainty without assuming measured accuracy or fixed latency.
Load or copy the skills/mcplaya-decisions folder using your agent's supported
skill mechanism. Its references are self-contained; optional agents/openai.yaml
provides Codex UI metadata. Native-layout export profiles and ZIP packages are
available for Codex, Claude Code, Cursor, GitHub Copilot, OpenCode, Gemini CLI,
Cline and Roo Code. See the harness guide for the discovery
paths, official sources and usage instructions.
uv run --frozen python scripts/export_usage_skill.py --harness allThe exporter creates one ZIP per harness under dist/, using one shared skill
and its references. It is a usage skill, independent of the separate
installation skill. It does not install, configure or launch the MCP server.
The repository and source distribution include the skill; the Python wheel
installs the server, so load the skill separately into the client.
Development
uv sync --frozen --extra dev --python 3.12
uv run --frozen --extra dev python -m pytest
uv run --frozen --extra dev python scripts/validate_usage_skill.py
uv run --frozen --extra dev python scripts/export_usage_skill.py --harness all
uv run --frozen --extra dev python -m buildLicense
Laya's code and the three official checkpoint cards declare Apache-2.0, allowing commercial use and redistribution with conditions. See docs/LICENSING.md for sources, obligations and the distinction between this wrapper and dependencies. This repository redistributes neither Laya code nor model weights.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
The decision layer for AI agents: act, escalate or refuse, and every decision comes back signed.
Signed, append-only receipts of an AI agent's decisions and outcomes, with public proof links.
Decision memory for AI agents: record, revisit, and resolve consequential choices.
Deterministic contextual decision arbitration and action routing for autonomous software. Takes current state, context, or intent plus caller-supplied candidate actions, state transitions, routes, refusals, escalations, tools, or models and returns a deterministic ordered candidate field. Also provides persistent machine representations for memory, retrieval, indexing, and downstream coherence measurement.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceLocal-first AI agent for approval-gated automation and verifiable LLM workflows.1MIT
- AlicenseAqualityBmaintenanceEnables AI agents to gate real-world side effects through a durable decision record, ensuring at-most-once initiation, deduplication, budget enforcement, and auditable outcomes across retries and failures.1562 npmApache 2.0

genpark-jev-system1official
AlicenseNot gradedqualityBmaintenanceEnables AI agents to resolve typed routing, loop-stall arbitration, and tool safety checks locally at sub-millisecond latency, avoiding unnecessary frontier LLM calls. It enforces reversible execution checkpoints, token budgets, and decayed episodic memory for safe, privacy-first autonomous operation.7MIT- AlicenseNot gradedqualityNot gradedmaintenanceEnables agents to resolve routine typed routing, loop-stall arbitration, and tool safety checks locally instead of invoking a frontier LLM, returning schema-enforced decision outputs and telemetry at sub-millisecond latency. Also provides reversible execution checkpoints, token budgets, and decay-based episodic memory for safe, privacy-preserving autonomous operation.MIT