Maid MCP Server

Fast, accurate Mermaid diagram validator (CLI) with clear diagnostics.

Local serverstdioTypeScript

What is the Maid MCP server?

Fast, accurate Mermaid diagram validator (CLI) with clear diagnostics. Exposed over MCP by the maid mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

Fast, accurate Mermaid diagram validator with clear, actionable diagnostics. Built for the AI age where Mermaid has become essential—but validation shouldn't require a browser.

  • Built for AI — Designed for AI agents and LLMs that generate Mermaid diagrams
  • Render Guarantee — When Maid says it's valid, your diagram will render
  • Lightning Fast — Validates in milliseconds without launching a browser
  • Human-Friendly — Clear error messages with line numbers, carets, and actionable hints
  • Lightweight — ~5MB vs. mermaid-cli's 1.7GB (Puppeteer + Chrome)
  • Auto-Fix — Automatically corrects common AI-generated mistakes

Its toolset

Everything the assistant can do here goes through one of these:

  • Mermaid.js — ~400KB (CDN) or 1.7GB (mermaid-cli + Puppeteer)
  • Development — The Development tool exposed by this server

Adding it to your client

@probelabs/maid on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Configuration

You will need one environment variable: LINK_ID. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

When to reach for it

Plenty of browser automation servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Maid's toolset — Mermaid.js, Development — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the maid mcp server does with a few real requests.

Available tools

ToolWhat it does
Mermaid.js~400KB (CDN) or 1.7GB (mermaid-cli + Puppeteer)
DevelopmentThe Development tool exposed by this server.

How to install the Maid MCP server

{
  "mcpServers": {
    "maid": {
      "command": "npx",
      "args": ["-y", "@probelabs/maid"],
      "env": {
        "LINK_ID": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
LINK_IDConfiguration value read at startup.Optional

Example prompts to try

  • Use Maid to Mermaid.js.
  • Use Maid to Development.

Frequently asked questions

It connects Maid to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (Mermaid.js, Development) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Maid directly.