Look twice.Find the gem.

AI agents and MCP servers, each published with its source and what the checks found.

Marketplace

  • Everything
  • AI agents
  • Apps
  • MCP servers
  • Templates
  • What people want
  • What changed this week
  • The verification standard
  • The ooruby Index
  • Servers that publish no source
  • Reliability guides
  • What the catalogue holds
  • Sell here

Our library

  • Everything, in one place
  • Guides
  • Glossary
  • Calculators
  • Checklists and cheat sheets
  • Community

ooruby

  • Home
  • For teams
  • Site status
  • Company projects
  • RSS feed

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.

AI agentsAppsMCP serversTemplatesWantedCommunityOur library
Sign inSell
Catalogue/MCP servers/Laya MCP

Laya MCP

perrylink · MCP server

Laya MCP is a Node entry point for a Python MCP server built around Laya, a PyTorch model that answers typed decisions: yes or no, a choice among options, or a score. It can run the model as a warm local sidecar, report what text would be cut, return errors that name the offending question, explain what its confidence value means, and flag a fall back to CPU. The Python side is installed separately. It is a work in progress and its interfaces may change.

Written by ooruby from the README of laya-mcp 0.1.5.

Not claimed by its maker. Is this yours? Prove it and answer the findings

Why it's useful

Your agent gets typed decisions from a local model, and you can see when input was cut or the model fell back to CPU.

What you could do with it

  1. 1Ask the model a yes or no question about a document and see first what text would be cut.
  2. 2Pick one option from a list of choices and read the confidence value that comes with it.
  3. 3Run a health check to see whether the model is really on the GPU or has dropped to CPU.

Written from its documentation: what it says it can do, not what our checks found.

LAMCP serverDeveloper tools

Maintenance

Not measured

No release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.

Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured

Not yet tested
Command execution is bounded
inventory
node child_process (bin/laya-mcp.js:28)
An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.
Data handling disclosed
finding
no statement of what it reads, writes or sends (README.md)

Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.

What this does not cover

  • ·Everything. Treat it as you would software from anywhere else.

Receipt history: every signed receipt for every version of this listing, and what changed between them.

In its maker's words

MCP server for Laya typed decisions (noul / choice / score): a warm model sidecar, token-budget preflight, and honest confidence. Node entry point for the Python package.

Compare with

  • Lara MCPside by side
  • Agent Deviceside by side
  • MCP Gitlabside by side
Compare all 4

How far this has been checked

Static scanned

What it establishes
Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
What it does not
How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
Exactly what was read
Version 0.1.5, the file with digest sha512-oetrg9qGkuCtgUIIK4ejFX2wbMVnxruNYkp6B3rXGV3rpRFDhEZJQ1ZbXvb8Vw1+kxORTpCQqXms8eJ1L/FFGg==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
Authentication
Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
How the rungs work

Adding it

Paste this into your client's MCP configuration.

{
  "mcpServers": {
    "laya-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "laya-mcp@0.1.5"
      ]
    }
  }
}

Or run it directly.

npx -y laya-mcp@0.1.5

Pinned to 0.1.5, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.

Where this came from

Registry
npm
Package
laya-mcp
Version read
0.1.5
Resolved
2026-10-10
Open the source(opens in a new tab)

No build provenance published. The repository above is the one the publisher declared, and nothing links it to the package you would install. That is not a mark against this listing, since most packages are published this way, but it is a check nobody can run.

The badge, if this is your listing

It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.

[![ooruby: static scanned](https://ooruby.com/api/badge/laya-mcp)](https://ooruby.com/market/laya-mcp)

About this listing

Kind
MCP server
Category
Developer tools
Pricing
Free
Sandbox
No
Hosted
No
Updated
2026-10-06
Price
Free
Get it freeVisit maker
Rating
no reviews yet
0 want this so far
Sign in to vote

Sign in to watch this listing and hear when its version, rung or findings change.

More from perrylink

See the storefront
DAappDeveloper tools
4 findingsStatic scanned
A read-only reviewer subagent reads the workspace, the tool call arguments and your risk rules, then returns a verdict with a reason. Per-tool policies choose who answers each request.

Dsh Auto Review

perrylink
Free

Has a second AI model review DeepSeek Harness approval requests and allow or deny each one.

7.1k installs/moApache-2.0
DMagentDeveloper tools
Clean scanStatic scanned
Memory sits in a local SQLite database in two tracks, one for facts about you and one for the agent, each with user-wide and workspace layers. Hard character budgets cap each store.

Dsh Memento

perrylink
Free

Adds cross-session memory to DeepSeek Harness, with every memory write routed through an approval step.

5.9k installs/moApache-2.0
DCMCP serverDeveloper tools
Clean scanStatic scanned
Read-only. It returns a plugin's full certification record, lists every entry in the public registry and summarises the certification spec. Its snapshot refreshes from the registry at most once every five minutes.

Dsh Cert MCP

perrylink
Free

Lets your agent look up the certification grade and evidence for a DeepSeek Harness plugin.

1.4k installs/moApache-2.0

Similar MCP servers

All MCP servers
STMCP serverDeveloper tools
2 findingsStatic scanned
A library rather than a ready-made server: it builds an HTTP handler whose tools list your components, show a component's docs and show a single story, read from Storybook manifests.

Storybook MCP

storybook
Free

Adds Storybook component and story documentation tools to an MCP server you run yourself.

9.4M installs/moMIT
CDMCP serverDeveloper tools
Clean scanStatic scanned
Uses Puppeteer to act in the page and wait for results. It turns performance traces into insights, analyses network requests, takes screenshots and shows console messages with source-mapped stack traces.

Chrome Devtools MCP

mathias
Free

Lets your agent control and inspect a live Chrome browser using Chrome DevTools.

9.9M installs/moApache-2.0
COMCP serverDeveloper tools
Clean scanStatic scanned
One tool resolves a library name to an identifier and another fetches the documentation for it, optionally focused on a topic and fetched page by page. An API key raises rate limits and adds private repositories.

Context7 MCP

upstash
Free

Pulls version-specific library docs and code examples straight into your agent's context.

3.9M installs/moMIT

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.