What can you do with this server?

This server lets you manage magic-api instances via MCP, covering API lifecycle management, group/function/datasource administration, and built-in magic-script knowledge. API Management * list_apis – List all interfaces (optionally filter by group) * get_api – Retrieve full details (including script) by id, name, or path * create_api – Create a new interface; auto-creates missing groups * update_api_script – Update the script of an existing interface * delete_api – Delete an interface by id, name, or path * run_api – Execute/test an interface, returning status, headers, and body Group Management * list_groups – List all groups/folders * create_group – Create a new group with name, path, optional type, and optional parent Function Management * list_functions – List all magic-script functions * get_function – Get full details of a function by id or name Datasource Management * list_datasources – List all configured datasources Knowledge & Search * magic_script_help – Query built-in magic-script documentation by topic (e.g., db, http, pagination, transactions) * search_code – Full-text search across all interface and function scripts Additional Features * Read-only mode (MAGIC_API_READONLY=true): disables all write tools * Multi-target support (http mode): manage multiple magic-api instances (e.g., prod/dev) from one deployment * Two transport modes: stdio (local) and http (remote/team-shared)

Which integrations are available for this server?

Allows AI to operate a running magic-api instance, providing tools for API CRUD and execution, group/function/datasource management, and built-in magic-script knowledge.

How do I use magic-api-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@magic-api-mcp 列出所有接口分组，并查看getUser接口的脚本" 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.

magic-api-mcp

by LynxBay

Overview Schema Related Servers Score Discussions

TypeScript

Hybrid

magic-api MCP

让 AI 通过 MCP 操作运行中的 magic-api 实例：接口增删改查 + 运行、分组 / 函数 / 数据源管理，并内置 magic-script 知识。

支持两种部署：

stdio：本地跑，Claude 启动子进程（适合个人开发机）
http：远程服务，全公司 / 团队共用一个（适合集中部署）

安装

cd magic-api-mcp
npm install
npm run build

Related MCP server: magic-api-mcp-server

配置（环境变量）

变量	必填	默认	说明
`MAGIC_API_BASE`	是	—	magic-api 地址，如 `http://your-magic-api-host:9999`
`MAGIC_API_WEB`	否	`/magic/web`	管理端路径（非默认实例要改，如 `/your-app/magic/dev`）
`MAGIC_API_TOKEN`	否*	—	静态 token
`MAGIC_API_USERNAME` / `MAGIC_API_PASSWORD`	否*	—	账号密码（自动 login）
`MAGIC_API_READONLY`	否	`false`	只读模式，禁用写工具
`MAGIC_API_PREFIX`	否	空	接口路径前缀
`MAGIC_API_TRANSPORT`	否	`stdio`	`stdio` 或 `http`
`MAGIC_API_HTTP_PORT`	否	`3111`	http 模式监听端口
`MAGIC_API_HTTP_HOST`	否	`0.0.0.0`	http 模式监听地址
`MAGIC_API_ACCESS_TOKEN`	否	—	http 模式访问令牌（Bearer），不设则不鉴权

* 鉴权二选一（账号密码优先）。

多 target（一套服务操作多个 magic-api 实例）

如果同一个 MCP 部署需要操作多个 magic-api 实例（如 prod / dev），无需再部署多套，用 MAGIC_API_TARGETS 声明即可。

原理： 目标实例由 URL path 选定（/mcp/<target>），path 写死在 claude mcp add 命令里，整个 session 不可变，AI 没有任何工具能跨 target——选择权完全在人手里。

服务端（多 target 启动）：

MAGIC_API_TARGETS=prod,dev \
MAGIC_API_TARGET_PROD_BASE=http://prod-host:9999 \
MAGIC_API_TARGET_PROD_TOKEN=静态令牌 \
MAGIC_API_TARGET_PROD_READONLY=true \
MAGIC_API_TARGET_DEV_BASE=http://dev-host:9999 \
MAGIC_API_TARGET_DEV_USERNAME=admin \
MAGIC_API_TARGET_DEV_PASSWORD=密码 \
MAGIC_API_TRANSPORT=http \
MAGIC_API_ACCESS_TOKEN=团队令牌 \
node dist/index.js

每 target 的字段（前缀为 MAGIC_API_TARGET_<NAME>_，NAME 转为大写）：

变量	必填	默认	说明
`_BASE`	target 必填	—	magic-api 地址
`_WEB`	否	`/magic/web`	管理端路径
`_TOKEN`	否*	—	静态 token
`_USERNAME` / `_PASSWORD`	否*	—	账号密码（自动 login）
`_READONLY`	否	`false`	只读模式
`_PREFIX`	否	空	接口路径前缀

同事连接（每人按需选 target）：

# 连生产
claude mcp add --transport http magic-api-prod http://部署机:3111/mcp/prod \
  --header "Authorization: Bearer 团队令牌"

# 连开发
claude mcp add --transport http magic-api-dev http://部署机:3111/mcp/dev \
  --header "Authorization: Bearer 团队令牌"

target 名仅允许 [A-Za-z0-9_-]+，同一 session 锁定一个 target。
不设 MAGIC_API_TARGETS 时仍为单 target（legacy 模式），现有部署零改动。
stdio 不支持多 target（无 path 路由），设了 MAGIC_API_TARGETS 又用 stdio 会启动报错。
全局 MAGIC_API_ACCESS_TOKEN 守卫所有 path；per-target 隔离由 URL 完成。

模式一：stdio（本地，个人用）

Claude 直接启动本地进程。

Claude Code

claude mcp add magic-api --scope user \
  -e MAGIC_API_BASE=http://your-magic-api-host:9999 \
  -e MAGIC_API_WEB=/your-app/magic/dev \
  -e MAGIC_API_USERNAME=your-username \
  -e MAGIC_API_PASSWORD=your-password \
  -- node /绝对路径/magic-api-mcp/dist/index.js

Claude Desktop（claude_desktop_config.json）

{
  "mcpServers": {
    "magic-api": {
      "command": "node",
      "args": ["/绝对路径/magic-api-mcp/dist/index.js"],
      "env": {
        "MAGIC_API_BASE": "http://your-magic-api-host:9999",
        "MAGIC_API_WEB": "/your-app/magic/dev",
        "MAGIC_API_USERNAME": "your-username",
        "MAGIC_API_PASSWORD": "your-password"
      }
    }
  }
}

模式二：http（远程，团队共用）

在一台服务器（如内网）常驻运行，所有人连同一个地址。凭据集中在服务端，客户端无需知道 magic-api 密码。

直接启动

MAGIC_API_TRANSPORT=http \
MAGIC_API_HTTP_PORT=3111 \
MAGIC_API_ACCESS_TOKEN=团队令牌 \
MAGIC_API_BASE=http://your-magic-api-host:9999 \
MAGIC_API_WEB=/your-app/magic/dev \
MAGIC_API_USERNAME=your-username \
MAGIC_API_PASSWORD=your-password \
node dist/index.js

常驻（pm2）

pm2 start dist/index.js --name magic-api-mcp
pm2 save && pm2 startup

Docker

docker build -t magic-api-mcp .
docker run -d -p 3111:3111 \
  -e MAGIC_API_BASE=http://your-magic-api-host:9999 \
  -e MAGIC_API_WEB=/your-app/magic/dev \
  -e MAGIC_API_USERNAME=your-username -e MAGIC_API_PASSWORD=your-password \
  -e MAGIC_API_ACCESS_TOKEN=团队令牌 \
  magic-api-mcp

同事的 Claude Code 连接

claude mcp add --transport http magic-api http://部署机:3111/mcp \
  --header "Authorization: Bearer 团队令牌"

http 模式为无状态（每个请求独立 transport），适合低频管理操作。强烈建议设置 MAGIC_API_ACCESS_TOKEN，否则任何能访问该端口的人都能操作 magic-api。

工具一览

接口：list_apis get_api create_api update_api_script delete_api run_api
分组：list_groups create_group
函数：list_functions get_function
数据源：list_datasources
知识：magic_script_help search_code

只读模式（MAGIC_API_READONLY=true）下，写工具被隐藏并在调用时拒绝。

冒烟测试

手动脚本（只读，对真实实例）：

MAGIC_API_BASE=... MAGIC_API_WEB=... MAGIC_API_USERNAME=... MAGIC_API_PASSWORD=... \
node scripts/smoke.mjs

或接进 Claude 后试：「列出所有接口分组，看看 getPrintData 的脚本」。

开发

npm test        # 单元 + 集成（73 测试）
npm run dev     # tsx 直跑（stdio）
npm run build

Install Server

license - not found

quality

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

–Release cycle

–Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Tools

View all tools

Latest Blog Posts

Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly
Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
OpenAI
open source

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/LynxBay/magic-api-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server