mcpField
Y
YApi MCP

YApi MCP

Local
github.com/ContextDongDeveloper Tools0Updated 2w ago

About YApi MCP

YApi MCP retrieves JSON API documentation from YApi projects for coding agents integrating client projects. It supports searchable interface catalogs, normalized request and response definitions, and several credential configuration methods.

Key features

  1. 01Parse YApi project URLs
  2. 02List and search interfaces
  3. 03Export interface catalogs
  4. 04Retrieve normalized request and response JSON
  5. 05Configure credentials at runtime or from files

Use cases

  1. 01Find an interface in a YApi project
  2. 02Inspect request and response schemas before implementation
  3. 03Export an API catalog
  4. 04Configure project credentials for documentation access

MCP support

Exposes YApi project and interface operations as MCP tools, including configuration, URL parsing, interface search, detail retrieval, and catalog export.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"contextdong-yapi": {
"command": "uvx",
"args": [
"contextdong-yapi-mcp"
],
"env": {
"YAPI_BASE_URL": "<YAPI_BASE_URL>",
"YAPI_TOKEN": "<YAPI_TOKEN>",
"YAPI_UID": "<YAPI_UID>"
}
}
}
}
Run commanduvx contextdong-yapi-mcp
Environment variables to set
YAPI_BASE_URLYApi host URL, e.g. https://yapi.example.com
YAPI_TOKENSecretLogin JWT or project open token
YAPI_UIDOptional uid for login JWT cookie auth

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypicontextdong-yapi-mcp0.1.0

Tools

7

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
uidanyNo
tokenanyNo
cookieanyNo
timeoutanyNo
base_urlanyNo
clear_secretsbooleanNo

Details

From the project README

Yapi-Mcp

从粘贴的 YApi 项目地址拉取接口文档(JSON 请求 / JSON 响应),供编码 Agent 自动理解并对接客户端项目的 MCP Server。

English

功能

  • 解析 YApi 页面 URL → base_url / project_id / interface_id
  • 列出 / 搜索接口,导出目录
  • 拉取归一化后的请求与响应 JSON(JSON Schema / 示例)
  • 鉴权:登录 JWT(Cookie _yapi_token + _yapi_uid)或项目 open token
  • 动态凭证:环境变量、.env、.yapi-mcp.json、运行时 yapi_configure、或工具参数

快速接入

Cursor / Claude Desktop MCP
{
  "mcpServers": {
    "yapi": {
      "command": "uvx",
      "args": ["--from", "contextdong-yapi-mcp", "yapi-mcp"],
      "env": {
        "YAPI_BASE_URL": "https://yapi.example.com",
        "YAPI_TOKEN": "YOUR_LOGIN_JWT_OR_PROJECT_OPEN_TOKEN"
      }
    }
  }
}

从 Git 安装(不经 PyPI):

{
  "mcpServers": {
    "yapi": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/ContextDong/Yapi-Mcp",
        "yapi-mcp"
      ],
      "env": {
        "YAPI_BASE_URL": "https://yapi.example.com",
        "YAPI_TOKEN": "YOUR_TOKEN"
      }
    }
  }
}

或使用 pip:

pip install contextdong-yapi-mcp
# 或: pip install git+https://github.com/ContextDong/Yapi-Mcp

配置凭证(仓库内不存放密钥)

优先级从高到低:

  1. 工具参数(token、base_url)
  2. 运行时 yapi_configure(仅当前 MCP 进程内存)
  3. 环境变量 / .env(YAPI_BASE_URL、YAPI_TOKEN、YAPI_UID、YAPI_COOKIE)
  4. 配置文件 .yapi-mcp.json,或 YAPI_MCP_CONFIG 指向的路径

示例:

cp .env.example .env
cp .yapi-mcp.example.json .yapi-mcp.json
变量说明
YAPI_BASE_URLYApi 主机,如 https://yapi.example.com
YAPI_TOKEN登录 JWT 或 项目 open token
YAPI_UID可选;登录 JWT 一般会自动解析 uid
YAPI_COOKIE可选;原始 Cookie 头覆盖
YAPI_MCP_CONFIG可选;JSON 配置文件路径

切勿提交 .env、.yapi-mcp.json 或真实 token。

工具列表

工具用途
yapi_configure / yapi_get_config动态配置 / 查看非敏感配置
yapi_parse_url从页面 URL 解析主机与 id
yapi_get_project项目元信息
yapi_list_interfaces可搜索的接口索引
yapi_get_interface单个接口完整 JSON 定义(便于写客户端)
yapi_export_catalog导出目录(可选详情)

Agent 用法

在对话中粘贴项目地址:

根据 https://yapi.example.com/project/123/interface/api/ 对接登录相关接口

Agent 应先配置凭证(如需要),再列表 / 拉详情,最后按目标工程现有风格实现客户端。

可选 Skill:.cursor/skills/yapi-api-client/SKILL.md

本地开发

python -m pip install -e ".[dev]"
python -m pytest
python -m yapi_mcp.server

MCP Registry

  • 官方名:io.github.ContextDong/yapi-mcp
  • PyPI 包:contextdong-yapi-mcp(uvx / 命令 yapi-mcp)
  • 说明:短名 yapi-mcp 在 PyPI 上已被其他项目占用

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.