Skip to main content
Glama

AsyncAPI MCP Server

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.

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

Related MCP server: EasyPeasyMCP

Quick Start

Remote (Hosted, no signup required)

The server runs a free public instance at https://asyncapi-mcp.onrender.com — no account, no API key. Just point your client at it.

Claude Code:

claude plugin marketplace add Souvikns/asyncapi-mcp

Then, inside a Claude Code session:

/plugin install asyncapi-mcp@asyncapi-mcp

Any other MCP client — add this to your MCP client configuration:

{
  "mcpServers": {
    "asyncapi": {
      "url": "https://asyncapi-mcp.onrender.com/mcp"
    }
  }
}

See the Configuration section below for client-specific instructions, and the Deployment section if you'd rather run your own instance.

Local (Self-hosted)

Prerequisites

Install

npm install

Build

npm run build

Run

Streamable HTTP (for local development):

npm run dev

The server starts on http://localhost:3000/mcp by default, and the website is served at http://localhost:3000/. Set the PORT environment variable to use a different port:

PORT=8080 npm run dev

Stdio (for local MCP clients):

npm run start:stdio

Available Tools

Tool

Description

Parameters

list_asyncapi_spec_versions

List stable AsyncAPI spec versions available as GitHub tags

None

get_asyncapi_spec_metadata

Return source, version, cache, and size metadata for a spec

version (optional)

search_asyncapi_spec

Search the spec and return matching snippets

query (required), version (optional), limit (default: 10, max: 20)

validate_asyncapi_spec

Validate raw AsyncAPI YAML or JSON content and return validation errors

spec (required)

get_asyncapi_spec_section

Return a section by heading text or slug

heading (required), version (optional)

Available Resources

Resource

URI

Description

Latest AsyncAPI Spec

asyncapi://spec/latest

The latest AsyncAPI markdown specification from the master branch

AsyncAPI Spec by Version

asyncapi://spec/{version}

A specific version of the spec fetched from the matching GitHub release tag

Rate Limiting

The /mcp endpoint has no authentication — it's rate-limited per IP address instead (60 requests per minute by default). Exceeding the limit returns a 429 response with a Retry-After header. The /health endpoint is never rate-limited, so platform health checks always succeed. Limits are configurable via the RATE_LIMIT_MAX and RATE_LIMIT_WINDOW_MS environment variables if you're running your own instance. Behind a reverse proxy (like Render's), set TRUST_PROXY_HOPS to the number of proxy hops in front of the app (verify by logging the effective config — see the startup log) so IP-based limiting isn't trivially bypassable, and set ALLOWED_HOSTS to your public hostname(s) (comma-separated) to restore DNS-rebinding protection.

Configuration for AI Coding Tools

Remote (Render hosted)

Use these configs to connect to the hosted instance at https://asyncapi-mcp.onrender.com — no setup or API key required. Running your own instance instead? Swap in your own URL (see Deployment).

Claude Code

From your terminal, add the marketplace:

claude plugin marketplace add Souvikns/asyncapi-mcp

Then, inside a Claude Code session, install the plugin:

/plugin install asyncapi-mcp@asyncapi-mcp

Claude Desktop

{
  "mcpServers": {
    "asyncapi": {
      "url": "https://asyncapi-mcp.onrender.com/mcp"
    }
  }
}

Cursor

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

{
  "mcpServers": {
    "asyncapi": {
      "url": "https://asyncapi-mcp.onrender.com/mcp"
    }
  }
}

VS Code Copilot

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

{
  "servers": {
    "asyncapi": {
      "url": "https://asyncapi-mcp.onrender.com/mcp",
      "type": "http"
    }
  }
}

Windsurf

Add to your Windsurf MCP settings:

{
  "mcpServers": {
    "asyncapi": {
      "serverUrl": "https://asyncapi-mcp.onrender.com/mcp"
    }
  }
}

Cline

In Cline's MCP settings, add:

{
  "mcpServers": {
    "asyncapi": {
      "url": "https://asyncapi-mcp.onrender.com/mcp"
    }
  }
}

OpenCode

Add to your OpenCode configuration:

{
  "mcp": {
    "servers": {
      "asyncapi": {
        "url": "https://asyncapi-mcp.onrender.com/mcp"
      }
    }
  }
}

Zed

Add to your Zed settings.json:

{
  "context_servers": {
    "asyncapi": {
      "url": "https://asyncapi-mcp.onrender.com/mcp"
    }
  }
}

Local (Self-hosted)

Use these configs when running the server locally with npm run dev. Make sure the server is running before connecting — no signup or API key needed.

Cursor / Claude Desktop

{
  "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 Render URL in the configs above with http://localhost:3000/mcp.

Deployment

Render provides a free web service tier with no credit card required. This is the easiest way to host your MCP server.

Free tier behavior

  • 750 free instance hours per month — plenty for a single MCP server

  • Sleeps after 15 minutes of idle time — the service spins down when nobody is using it

  • Wakes up on next request — takes about 30–60 seconds to respond after sleep

  • No credit card required — truly $0

Prerequisites

Deploy via Git

  1. In the Render dashboard, click New → Web Service.

  2. Connect your GitHub account and select your repository.

  3. Render will auto-detect the Node.js buildpack.

  4. Set the following:

    • Name: asyncapi-mcp (or whatever you prefer)

    • Runtime: Node

    • Build Command: npm install && npm run build

    • Start Command: npm start

    • Instance Type: Free

  5. Add environment variables:

    • PORT = 3000

    • NODE_ENV = production

    • TRUST_PROXY_HOPS = 1 (verify this against Render's actual proxy chain post-deploy — see Rate Limiting)

    • ALLOWED_HOSTS = asyncapi-mcp.onrender.com (restores DNS-rebinding protection; use your own domain if self-hosting under a different one)

  6. Click Create Web Service.

Render will build and deploy your app. Once finished, you'll get a public URL like https://asyncapi-mcp.onrender.com — visiting it shows the website, and the server is immediately usable with no signup step.

Publish it as a Claude Code plugin

This repo already includes .claude-plugin/plugin.json and .claude-plugin/marketplace.json. If you deploy your own instance, update the url in .claude-plugin/plugin.json to point at your Render URL. Anyone can then install it in two steps: first, from a terminal, add your fork as a marketplace —

claude plugin marketplace add <your-github-username>/<your-repo>

— and then, inside a Claude Code session (not a shell — this is a Claude Code slash command), install the plugin from it:

/plugin install asyncapi-mcp@asyncapi-mcp

Configure your MCP client

Your Render domain is already configured in the Configuration section above.

Health check

You can verify the server is running by visiting:

https://asyncapi-mcp.onrender.com/health

Self-hosted (Docker)

Build and run with the included Dockerfile:

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

The HTTP server will be available at http://localhost:3000/mcp and the website at http://localhost:3000/.

Self-hosted (Local machine)

npm install
npm run build
npm start

The server starts on http://localhost:3000/mcp by default.

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

Setup

Requires Node.js v20+:

npm install
npm run build
npm run dev

This builds the website on first run and starts the server. Then visit http://localhost:3000, or use http://localhost:3000/mcp directly in your MCP client config — no signup or API key needed.

# In another terminal: run the website dev server with hot reload
npm run dev:web

# Build TypeScript to dist/ and the website to web/dist/
npm run build

# Run the stdio server (for local MCP clients)
npm run start:stdio

# Type-check without emitting
npx tsc --noEmit

Available Tools

5 tools
get_asyncapi_spec_metadataGet AsyncAPI Spec MetadataA

Return source, version, cache, and size metadata for the latest AsyncAPI specification.

Inputs: version.

get_asyncapi_spec_sectionGet AsyncAPI Spec SectionA

Return one section from the latest AsyncAPI markdown specification by heading text or slug.

Inputs: heading (required), version.

list_asyncapi_spec_versionsList AsyncAPI Spec VersionsA

List stable AsyncAPI specification versions available as GitHub tags.

Inputs: no named parameters.

search_asyncapi_specSearch AsyncAPI SpecA

Search the latest AsyncAPI markdown specification and return matching snippets.

Inputs: query (required), version, limit.

validate_asyncapi_specValidate AsyncAPI SpecB

Validate raw AsyncAPI YAML or JSON content and return validation errors if the spec is invalid.

Inputs: spec (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool serves a distinct purpose: metadata retrieval, section access, version listing, search, and validation. No overlap in functionality.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern with snake_case, such as 'get_asyncapi_spec_metadata' and 'validate_asyncapi_spec', making it predictable.

    Tool Count5/5

    With 5 tools, the server covers the core operations for an AsyncAPI spec explorer without being too sparse or excessive.

    Completeness4/5

    The tool set covers metadata, sections, versions, search, and validation. Minor gap: no direct way to retrieve the entire raw spec, though sections and search can compensate.

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that enables AI agents to search, discover, and retrieve technical specifications from a SpecLib instance. It provides tools for full-text search, scope listing, and reading specs as markdown content.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      A lightweight, zero-config MCP server that makes documentation and API specifications instantly accessible to AI models using the llms.txt standard. It enables searching and retrieving full documentation, OpenAPI, and AsyncAPI specs without requiring a complex RAG infrastructure or vector database.
      1
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server for AsyncAPI that enables parsing, validation, linting, conversion, model generation, and template generation from any MCP client using stdio.
      16 npm
      Apache 2.0