Skip to main content
Coming Soon — The @avala/mcp-server npm package is under active development and not yet published. The setup instructions below describe the planned integration. We’ll update this page when the package is available.
The Model Context Protocol (MCP) is an open standard that lets AI assistants call external tools and access data sources. Avala’s MCP server will expose your datasets, projects, and exports as tools, so you can manage your annotation workflow through natural language in Claude, Cursor, VS Code, or ChatGPT.
Avala already has an internal MCP endpoint (POST /api/v1/mcp/) with 22 database introspection and analytics tools. The planned @avala/mcp-server npm package will provide a standalone, customer-facing MCP server that wraps the REST API for use with AI assistants.

​
Prerequisites

  • Node.js 18 or later
  • An Avala API key (Mission Control → Settings → API Keys)

​
Claude Desktop

Open your Claude Desktop config file and add the Avala server:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "avala": {
      "command": "npx",
      "args": ["-y", "@avala/mcp-server"],
      "env": {
        "AVALA_API_KEY": "avala_sk_your_api_key"
      }
    }
  }
}
Restart Claude Desktop. The Avala tools will appear in the tool picker.

​
Cursor

Create or edit .cursor/mcp.json in your project root: 
{
  "mcpServers": {
    "avala": {
      "command": "npx",
      "args": ["-y", "@avala/mcp-server"],
      "env": {
        "AVALA_API_KEY": "avala_sk_your_api_key"
      }
    }
  }
}
Restart Cursor or reload the window. The tools will be available in agent mode.

​
What You Can Do

Once connected, you can ask your AI assistant to interact with Avala using natural language. Here are some example prompts: 
List all my datasets

Show the status of the "Pedestrian Detection" project

How many tasks are completed in "Lidar QA"?

Create a COCO export for dataset ds_abc123

Show my workspace stats
The assistant calls the appropriate Avala MCP tool, processes the response, and presents the results. You can chain multiple requests in a single conversation — for example, list datasets, pick one, then trigger an export.

​
Full Setup Guide

For VS Code, ChatGPT, and a complete list of available MCP tools, see the full MCP Server setup guide.

MCP Server Setup

Complete setup instructions for all supported AI clients and the full tool reference.

API Authentication

Create and manage the API keys used by the MCP server.