AsyncAPI-MCP
AsyncAPI MCP 服务器
一个 MCP(模型上下文协议)服务器,让 AI 助手能够访问 AsyncAPI 规范。直接从你的编码工具中搜索、探索并获取任何版本的规范。
在 Glama 浏览器中试用 — 无需安装。
功能
搜索:按关键字搜索 AsyncAPI 规范
获取:通过标题或 slug 获取特定章节
列出:列出所有作为 GitHub 标签提供的稳定规范版本
获取元数据:获取关于规范的元数据(版本、来源、缓存信息、大小)
版本感知:查询任何已发布的规范版本,或默认为最新版本
缓存:基于 ETag/Last-Modified 的 HTTP 缓存,标签查找具有 10 分钟的 TTL
Related MCP server: EasyPeasyMCP
快速入门
远程 (Glama)
使用 Glama 上托管的服务器 — 无需本地设置。将以下内容添加到你的 MCP 客户端配置中:
{
"mcpServers": {
"asyncapi": {
"url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
}
}
}请参阅下方的 配置 部分,了解特定客户端的说明。
本地 (自托管)
先决条件
Node.js v20 或更高版本
安装
npm install构建
npm run build运行
流式 HTTP(用于本地开发):
npm run dev服务器默认在 http://localhost:3000/mcp 启动。设置 PORT 环境变量以使用不同的端口:
PORT=8080 npm run devStdio(用于部署):
npm start可用工具
工具 | 描述 | 参数 |
| 列出作为 GitHub 标签提供的稳定 AsyncAPI 规范版本 | 无 |
| 返回规范的来源、版本、缓存和大小元数据 |
|
| 搜索规范并返回匹配的代码片段 |
|
| 验证原始 AsyncAPI YAML 或 JSON 内容并返回验证错误 |
|
| 通过标题文本或 slug 返回章节 |
|
可用资源
资源 | URI | 描述 |
最新 AsyncAPI 规范 |
| 来自 master 分支的最新 AsyncAPI Markdown 规范 |
按版本划分的 AsyncAPI 规范 |
| 从匹配的 GitHub 发布标签获取的特定版本规范 |
AI 编码工具配置
远程 (Glama 托管)
使用这些配置连接到 Glama 托管的服务器。无需本地设置。
Claude Desktop
添加到 ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) 或 %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"asyncapi": {
"url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
}
}
}Cursor
添加到项目根目录的 .cursor/mcp.json:
{
"mcpServers": {
"asyncapi": {
"url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
}
}
}VS Code Copilot
添加到项目根目录的 .vscode/mcp.json:
{
"servers": {
"asyncapi": {
"url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp",
"type": "http"
}
}
}Windsurf
添加到你的 Windsurf MCP 设置中:
{
"mcpServers": {
"asyncapi": {
"url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
}
}
}Cline
在 Cline 的 MCP 设置中,添加:
{
"mcpServers": {
"asyncapi": {
"url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
}
}
}OpenCode
添加到你的 OpenCode 配置中:
{
"mcp": {
"servers": {
"asyncapi": {
"url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
}
}
}
}Zed
添加到你的 Zed settings.json:
{
"context_servers": {
"asyncapi": {
"url": "https://glama.ai/mcp/servers/Souvikns/asyncapi-mcp"
}
}
}本地 (自托管)
在使用 npm run dev 本地运行服务器时使用这些配置。在连接前请确保服务器正在运行。
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
将上述配置中的 Glama URL 替换为 http://localhost:3000/mcp。
部署
此服务器部署在 Glama.ai 上。请参阅 glama.ai/mcp/servers/Souvikns/asyncapi-mcp 获取托管实例。
要部署你自己的实例,请使用 stdio 传输进行构建和运行:
npm run build
npm start包含一个 Dockerfile 用于容器化部署:
docker build -t asyncapi-mcp .
docker run -p 3000:3000 asyncapi-mcp使用示例
配置完成后,你可以向 AI 助手询问如下问题:
“AsyncAPI 规范中关于服务器对象(server objects)是怎么说的?”
“在 AsyncAPI 规范中搜索 'channels'”
“获取 2.6.0 版本中的 Info Object 章节”
“列出所有可用的 AsyncAPI 规范版本”
“AsyncAPI 2.x 和 3.x 中的消息有什么区别?”
“向我展示关于模式定义(schema definitions)的规范章节”
开发
# 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 --noEmitMaintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAn 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.
- AlicenseNot gradedqualityCmaintenanceA 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.221Apache 2.0
- AlicenseAqualityAmaintenanceMCP server that helps AI agents explore OpenAPI specs, search endpoints, and generate TypeScript types.721510MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server for AsyncAPI that enables parsing, validation, linting, conversion, model generation, and template generation from any MCP client using stdio.22Apache 2.0
Related MCP Connectors
An MCP server that gives your AI access to the source code and docs of all public github repos
MCP server for AI access to Swagger by SmartBear.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Souvikns/asyncapi-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server