Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@YApi MCP Server get details for interface ID 789"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A MCP (Model Context Protocol) server for accessing YApi interface documentation.
📝 Get interface details by ID
🔗 Support YApi URL auto-parsing
Related MCP server: YApi MCP Server
{
"mcpServers": {
"yapi": {
"command": "npx",
"args": ["-y", "yapi-mcp-server@latest"],
"env": {
"YAPI_BASE_URL": "http://your-yapi-server.com",
"YAPI_TOKEN": "your-yapi-token"
}
}
}
}YAPI_BASE_URL: Your YApi server URL
YAPI_TOKEN: YApi access token
Login to YApi → Profile Settings → Copy Token
Please get the information for this interface: http://localhost:40001/project/11/interface/api/23Please use yapi-get-interface tool to get details for interface ID 789MIT
根据接口ID获取接口详情
Inputs: interfaceId (required).
根据YApi URL获取接口详情，支持格式如：http://localhost:40001/project/11/interface/api/23
Inputs: url (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Scored across 2 tools
The two tools have clearly distinct purposes: one retrieves interface details by ID, while the other retrieves them by URL. There is no overlap or ambiguity between their functions, making it easy for an agent to select the correct tool based on the available input.
Both tools follow a consistent naming pattern: 'yapi-get-interface' with a suffix indicating the input type ('-by-url'). This verb_noun structure is uniform and predictable, enhancing readability and usability across the tool set.
With only 2 tools, the server feels under-scoped for a YApi (API management) domain. This minimal set lacks essential operations like creating, updating, or listing interfaces, which are typical for such systems, making it insufficient for comprehensive agent workflows.
The tool surface is severely incomplete for API management. It only provides retrieval methods (by ID and URL), missing critical CRUD operations such as create, update, delete, or list interfaces. This creates significant gaps that will likely cause agent failures in handling full lifecycle tasks.
Read-only HotAPI documentation: search integration guides and inspect OpenAPI operations.
Turn any task into the right API calls: discover, evaluate, and integrate public APIs.
Publish your API docs so AI assistants can look up endpoints and call your API correctly.
Search and read the Flowie Exchange API docs and OpenAPI contract. No sign-in needed.
