AsyncAPI

Glama MIT License TypeScript

An MCP (Model Context Protocol) server that gives AI assistants access to the AsyncAPI specification. Search, explore, and retrieve any version of the spec directly from your coding tool.

Try it in your browser on Glama — no installation required.

Features

• Search the AsyncAPI specification by keyword
• Retrieve specific sections by heading or slug
• List all stable spec versions available as GitHub tags
• Get metadata about the spec (version, source, cache info, size)
• Version-aware — query any released spec version, or default to the latest
• Caching — ETag/Last-Modified-based HTTP caching with a 10-minute TTL on tag lookups

Quick Start

Remote (Glama)

Use the hosted server on Glama — no local setup needed. Add the following to your MCP client configuration:

{
  "mcpServers": {
    "asyncapi": {
      "url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
    }
  }
}

See the Configuration section below for client-specific instructions.

Local (Self-hosted)

npm install

npm run build

npm run dev

PORT=8080 npm run dev

npm start

Available Tools

Available Resources

Configuration for AI Coding Tools

Remote (Glama hosted)

Use these configs to connect to the Glama-hosted server. No local setup required.

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "asyncapi": {
      "url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "asyncapi": {
      "url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
    }
  }
}

VS Code Copilot

Add to .vscode/mcp.json in your project root:

{
  "servers": {
    "asyncapi": {
      "url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp",
      "type": "http"
    }
  }
}

Windsurf

Add to your Windsurf MCP settings:

{
  "mcpServers": {
    "asyncapi": {
      "url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
    }
  }
}

Cline

In Cline's MCP settings, add:

{
  "mcpServers": {
    "asyncapi": {
      "url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
    }
  }
}

OpenCode

Add to your OpenCode configuration:

{
  "mcp": {
    "servers": {
      "asyncapi": {
        "url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
      }
    }
  }
}

Zed

Add to your Zed settings.json:

{
  "context_servers": {
    "asyncapi": {
      "url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
    }
  }
}

Local (Self-hosted)

Use these configs when running the server locally with npm run dev. Make sure the server is running before connecting.

Claude Desktop

{
  "mcpServers": {
    "asyncapi": {
      "url": "http://localhost:3000/mcp"
    }
  }
}

Cursor

{
  "mcpServers": {
    "asyncapi": {
      "url": "http://localhost:3000/mcp"
    }
  }
}

VS Code Copilot

{
  "servers": {
    "asyncapi": {
      "url": "http://localhost:3000/mcp",
      "type": "http"
    }
  }
}

Windsurf / Cline / OpenCode / Zed

Replace the Glama URL in the configs above with http://localhost:3000/mcp.

Deployment

This server is deployed on Glama.ai. See glama.ai/mcp/servers/Souvikns/asyncapi-mcp for the hosted instance.

To deploy your own instance, build and run with stdio transport:

npm run build
npm start

A Dockerfile is included for containerized deployments:

docker build -t asyncapi-mcp .
docker run -p 3000:3000 asyncapi-mcp

Usage Examples

Once configured, you can ask your AI assistant questions like:

• "What does the AsyncAPI spec say about server objects?"
• "Search the AsyncAPI spec for 'channels'"
• "Get the Info Object section from version 2.6.0"
• "List all available AsyncAPI spec versions"
• "What are the differences between messages in AsyncAPI 2.x and 3.x?"
• "Show me the spec section about schema definitions"

Development

# Install dependencies
npm install

# Build TypeScript to dist/
npm run build

# Run the HTTP server (local development)
npm run dev

# Run the stdio server (for deployment)
npm start

# Type-check without emitting
npx tsc --noEmit