VueUse MCP

MCP server that gives AI coding agents instant access to VueUse documentation — search composables, read docs, and get suggestions.

How It Works When You Code

This is an MCP (Model Context Protocol) server. When you connect it to an AI coding agent like Claude Code, the agent can automatically look up VueUse documentation while helping you write code.

For example, if you ask "help me track the mouse position in Vue," the agent will:

1. Call search_composables or suggest_composable to find relevant composables
2. Call get_composable_docs to read the full documentation for useMouse
3. Write code using the correct API, options, and types — without you needing to look anything up

You don't need to manually call any tools. The agent decides when to use them based on your questions.

Quick Start

Claude Code

claude mcp add vueuse-mcp node /path/to/vueuse-mcp/dist/index.js

Codex CLI

Add to your MCP config:

{
  "servers": {
    "vueuse": {
      "command": "node",
      "args": ["/path/to/vueuse-mcp/dist/index.js"]
    }
  }
}

OpenCode

Add to your opencode.json:

{
  "mcp": {
    "vueuse": {
      "command": "node",
      "args": ["/path/to/vueuse-mcp/dist/index.js"]
    }
  }
}

Available Tools

| Tool | Description | |------|-------------| | search_composables | Search by name, keyword, or concept. Returns ranked results with descriptions. | | get_composable_docs | Get full docs for a composable — signature, types, options, examples, related functions. | | suggest_composable | Describe a use case in natural language and get ranked suggestions with trade-offs. | | list_categories | List all categories with composable counts. Optionally filter by package. |

Keeping Data Fresh

The composable data is scraped from the VueUse GitHub repo. To update:

npm run scrape && npm run build

Set a GITHUB_TOKEN environment variable to avoid rate limits during scraping. See .env.example.

Development

git clone https://github.com/kovoor/vueuse-mcp.git
cd vueuse-mcp
npm install
npm run scrape    # fetch composable data from GitHub
npm run build     # compile TypeScript
npm start         # run the server

Contributing

See CONTRIBUTING.md for how to add tools, update the scrape pipeline, and submit PRs.