mcpField
V
vueuse-mcp

vueuse-mcp

Local
github.com/kovoorDeveloper Tools5Updated 35w ago
Repository

About vueuse-mcp

vueuse-mcp is an MCP server for coding agents working with VueUse. It provides searchable composable documentation and use-case-based suggestions, including API details and examples.

Key features

  1. 01Search composables by name or concept
  2. 02Retrieve signatures, types, options, and examples
  3. 03Suggest composables from natural-language use cases
  4. 04Browse categories and composable counts

Use cases

  1. 01Find a VueUse composable for a coding task
  2. 02Check a composable's API and usage examples
  3. 03Compare suggested composables for a described need

MCP support

Exposes VueUse search, documentation, suggestion, and category tools to MCP clients such as coding agents.

Configuration

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

mcp.json · Universal config
{
  "mcpServers": {
    "kovoor-vueuse": {
      "command": "npx",
      "args": [
        "-y",
        "vueuse-mcp"
      ]
    }
  }
}
Run commandnpx -y vueuse-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
npmvueuse-mcp1.0.0

Tools

4

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
limitnumberNoMax results to return (default 10)
querystringYesSearch query — function name, keyword, or concept
packagestringNoFilter by package (e.g. "core", "shared", "integrations")
categorystringNoFilter by category (e.g. "Browser", "State", "Sensors")

Details

From the project README

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 -- npx vueuse-mcp
Codex CLI

Add to your MCP config:

{
  "servers": {
    "vueuse": {
      "command": "npx",
      "args": ["vueuse-mcp"]
    }
  }
}
OpenCode

Add to your opencode.json:

{
  "mcp": {
    "vueuse": {
      "command": "npx",
      "args": ["vueuse-mcp"]
    }
  }
}

Available Tools

ToolDescription
search_composablesSearch by name, keyword, or concept. Returns ranked results with descriptions.
get_composable_docsGet full docs for a composable — signature, types, options, examples, related functions.
suggest_composableDescribe a use case in natural language and get ranked suggestions with trade-offs.
list_categoriesList 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.

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.