Yapi

A Model Context Protocol (MCP) Server for Yapi API management platform. This project provides seamless integration between AI assistants and Yapi, allowing you to query API documentation, search interfaces, and manage API information through natural language.

This MCP server provides the following tools for interacting with Yapi:

Choose one of the following environments:

- Java Environment: JDK 21+ and Maven 3.6+
- Docker Environment: Docker and Docker Compose

# Clone the repository git clone https://github.com/yyykf/yapi-mcp-server.git cd yapi-mcp-server # Configure Yapi URL and project tokens vim src/main/resources/application-mcp.yml # Build the project mvn clean package # Run the application java -jar target/yapi-mcp-server-0.0.1-SNAPSHOT.jar

# Clone the repository git clone https://github.com/yyykf/yapi-mcp-server.git cd yapi-mcp-server # Configure Yapi URL and project tokens vim src/main/resources/application-mcp.yml # Run with Docker Compose docker-compose up -d

Before running the application, you need to configure your Yapi connection settings insrc/main/resources/application-mcp.yml:

spring: cloud: openfeign: client: config: yapiClient: url: http://yapi.com # Replace with your Yapi URL yapi: project-tokens: 123456: "your-project-token-1" # Project ID: Token 789012: "your-project-token-2" # Add more projects as needed

Building Multi-Architecture Docker Images

If you need to build and push multi-architecture Docker images manually, use the provided script:

./build-and-push.sh <version> <docker-username> <docker-password>

./build-and-push.sh 1.0.0 myusername mypassword

This script will build images for bothamd64andarm64architectures and create a multi-architecture manifest.

For more detailed project documentation and insights, you can explore the project using DeepWiki:

Click the button below to automatically install the MCP server in Cursor:

Add the following configuration to your Cursor MCP settings file (mcp.json):

{ "mcpServers": { "yapi": { "url": "http://127.0.0.1:8888/sse" } } }

Once the application is running, you can check its health status:

curl http://localhost:8888/actuator/health

Or visithttp://localhost:8888/actuator/healthin your browser.

After setting up the MCP server in Cursor, you can use natural language to interact with your Yapi instance:

- "Show me all available projects"
- "List all API categories in project 123456"
- "Search for login APIs"
- "Get details of interface ID 789"
- "What's the cache status?"

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.

The MCP server for Bitrix24 provides AI assistants with structured access to the Bitrix24 API. It delivers up-to-date method descriptions, parameters, and valid values, allowing assistants to work with precise data instead of guesswork. This reduces code errors and accelerates Bitrix24 integration development.

A TypeScript MCP server to access Apifox API data via Stdio.

Provides API documentation from Apifox projects as a data source for AI programming tools that support MCP.

A tool to retrieve API interface information from YApi, with authentication configurable via environment variables.

Clix MCP Server for assisting Clix SDK/API integrations with semantic search across Clix docs and SDK source (iOS, Android, Flutter, React Native).

Check software end-of-life (EOL) dates and support status using the endoflife.date API to provide accurate lifecycle and security information.

Fetches API information from Feishu OpenAPI for seamless integration and management within an IDE.

Unified MCP server for Ignite UI — documentation, API, and CLI scaffolding