mcpField
M
Matra

Matra

Local
matrajs.comDeveloper Tools0Updated 1w ago
RepositoryVisit website

About Matra

Matra is an MCP server that packages Matra rich text editor documentation for AI tools. It provides searchable pages, Markdown reading, and documentation resources without fetching content at runtime.

Key features

  1. 01List documentation pages
  2. 02Search ranked pages with snippets
  3. 03Read pages as Markdown
  4. 04Expose pages as resources
  5. 05Bundle documentation at build time

Use cases

  1. 01Look up Matra commands and APIs
  2. 02Search extension documentation
  3. 03Give an AI tool access to offline documentation

MCP support

It exposes `list_docs`, `read_doc`, and `search_docs` tools, with each page also available as a resource. It supports stdio and HTTP transports.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "com-matrajs-matra": {
      "command": "npx",
      "args": [
        "-y",
        "@matrajs/mcp"
      ]
    }
  }
}
Run commandnpx -y @matrajs/mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@matrajs/mcp1.1.6

Tools

3

Saved tool list · updated 3w ago

This tool takes no parameters.

Details

From the project README

@matrajs/mcp

The Matra documentation as a Model Context Protocol server, so any AI tool can read it. Zero dependencies, like every other Matra package.

npx -y @matrajs/mcp            # stdio · what a desktop client spawns
npx -y @matrajs/mcp --http     # http://localhost:3333/mcp

Connect it, step by step

Claude Code

claude mcp add matra -- npx -y @matrajs/mcp

Claude Desktop — in claude_desktop_config.json:

{
  "mcpServers": {
    "matra": { "command": "npx", "args": ["-y", "@matrajs/mcp"] }
  }
}

Cursor — in .cursor/mcp.json, the same object under "mcpServers".

Codex — in ~/.codex/config.toml:

[mcp_servers.matra]
command = "npx"
args = ["-y", "@matrajs/mcp"]

Anything that speaks HTTP — run npx -y @matrajs/mcp --http 3333 and point the client at http://localhost:3333/mcp.

Then ask the tool something about Matra. It will call search_docs, read the page it needs, and answer from the documentation rather than from memory.

What it serves

ToolDoes
list_docsEvery page, with its slug and a one-line description.
read_doc { slug }One page, as Markdown.
search_docs { query, limit? }Ranked pages with a snippet each.

Every page is also a resource at matra://docs/<slug>.

The pages are the repository's Markdown — README, the engine notes, benchmarks, security, the changelog — and every page of matrajs.com/docs, converted to Markdown at build time and shipped inside the package. Nothing is fetched at runtime.

Use it from code

import { createServer } from '@matrajs/mcp'

const server = createServer(docs)
server.handle({ jsonrpc: '2.0', id: 1, method: 'tools/list' })

createServer is the protocol without a transport: one message in, one reply out. Put it behind whatever transport you already have.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.