Auto

v1.0.0Developer Toolsstable

Transform any OpenAPI/Swagger definition into a fully-featured Model Context Protocol (MCP) server

automcpai-integration
Share:
190
Stars
0
Downloads
0
Weekly
0/5

What is Auto?

Auto is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to transform any openapi/swagger definition into a fully-featured model context protocol (mcp) server

Transform any OpenAPI/Swagger definition into a fully-featured Model Context Protocol (MCP) server

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Transform any OpenAPI/Swagger definition into a fully-featur

Use Cases

Transform OpenAPI definitions into fully-featured MCP servers.
Generate MCP servers automatically from Swagger specifications.
brizzai

Maintainer

LicenseApache-2.0
Languagego
Versionv1.0.0
UpdatedMay 11, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx auto

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Auto

Auto MCP transforms any OpenAPI or Swagger specification into a fully functional Model Context Protocol server, automatically generating tool definitions from every documented API endpoint so AI agents can call REST APIs without custom integration code. It ships with an interactive TUI config builder for filtering and annotating endpoints, supports three transport modes (stdio, HTTP, and SSE), and handles bearer token, API key, basic auth, and OAuth 2.1 authentication. API platform teams and backend developers use auto-mcp to instantly expose existing services to Claude and other MCP clients by providing just a swagger.json file.

Prerequisites

  • Docker installed (recommended) or Go 1.21+ for building from source
  • An OpenAPI 2.0 (Swagger) or OpenAPI 3.x specification file in JSON format
  • API credentials for your upstream service (bearer token, API key, etc.)
  • An MCP-compatible client such as Claude Desktop
1

Obtain your OpenAPI/Swagger specification

Download or export the OpenAPI specification for the API you want to expose. Most APIs provide a swagger.json or openapi.json endpoint (e.g. https://api.example.com/swagger.json).

curl https://api.example.com/swagger.json -o swagger.json
2

(Optional) Use the MCP Config Builder to filter and annotate endpoints

Run the interactive TUI to customize which endpoints are exposed and improve their descriptions for better AI tool selection.

docker run --rm -it \
  -v $(pwd)/swagger.json:/server/swagger.json \
  ghcr.io/brizzai/auto-mcp:latest \
  mcp-config-builder --swagger-file=/server/swagger.json
3

Test the server in stdio mode

Run the auto-mcp container in stdio mode to verify it parses your spec and starts correctly before wiring it into Claude Desktop.

docker run --rm -i \
  -v $(pwd)/swagger.json:/server/swagger.json \
  ghcr.io/brizzai/auto-mcp:latest \
  --swagger-file=/server/swagger.json --mode=stdio
4

Configure Claude Desktop to use auto-mcp

Add the auto-mcp Docker container as an MCP server in your claude_desktop_config.json. Pass your API base URL and authentication token as environment variables or CLI flags.

{
  "mcpServers": {
    "auto-mcp": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "-v", "/path/to/swagger.json:/server/swagger.json",
        "-e", "AUTO_MCP_BEARER_TOKEN=your-api-token",
        "ghcr.io/brizzai/auto-mcp:latest",
        "--swagger-file=/server/swagger.json",
        "--mode=stdio"
      ]
    }
  }
}
5

Restart Claude Desktop and test

Relaunch Claude Desktop to load the auto-mcp server. Claude will see all API endpoints as individual tools derived from the OpenAPI spec's operation IDs and descriptions.

Auto Examples

Client configuration

Claude Desktop config running auto-mcp via Docker with a local Swagger file and bearer token auth

{
  "mcpServers": {
    "auto-mcp": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "-v", "/home/user/myapi/swagger.json:/server/swagger.json",
        "-e", "AUTO_MCP_BEARER_TOKEN=sk-myapitoken",
        "ghcr.io/brizzai/auto-mcp:latest",
        "--swagger-file=/server/swagger.json",
        "--mode=stdio"
      ]
    }
  }
}

Prompts to try

Once auto-mcp is connected, Claude can call API endpoints derived from the spec

- "List all available API operations on this server"
- "Call the GET /users endpoint and show me the first 10 results"
- "Create a new resource using the POST /items endpoint with name 'test'"
- "What authentication method does this API use?"

Troubleshooting Auto

Docker cannot mount the swagger.json file

Use an absolute path in the `-v` mount argument. Relative paths like `$(pwd)/swagger.json` work in a terminal but may not resolve correctly in Claude Desktop's launch environment. Use the full absolute path instead.

API calls fail with authentication errors

Ensure the correct auth environment variable is set. For bearer token auth use `AUTO_MCP_BEARER_TOKEN`, for API keys check the spec's security scheme name and use the corresponding `AUTO_MCP_` prefixed variable.

Too many tools generated, causing Claude to struggle with selection

Use the MCP Config Builder TUI (`mcp-config-builder --swagger-file=...`) to filter out unused endpoints and improve descriptions. Save the output as an adjustment file and pass it with `--adjustment-file=/server/adjustments.json`.

Frequently Asked Questions about Auto

What is Auto?

Auto is a Model Context Protocol (MCP) server that transform any openapi/swagger definition into a fully-featured model context protocol (mcp) server It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Auto?

Follow the installation instructions on the Auto GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Auto?

Auto works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Auto free to use?

Yes, Auto is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "auto": { "command": "npx", "args": ["-y", "auto"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Auto?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides