Apollo 配置中心的 MCP (Model Context Protocol) 服务
LocalAbout Apollo 配置中心的 MCP (Model Context Protocol) 服务
Apollo MCP Server lets language-model clients query and manage an Apollo configuration center using its Portal address and token. It covers applications, clusters, namespaces, configuration items, and releases, including publishing and rollback.
Key features
- 01List and manage applications
- 02Inspect and create clusters
- 03Browse and manage namespaces
- 04Create, update, and delete config items
- 05Publish and roll back releases
Use cases
- 01Finding configuration for a namespace
- 02Updating an Apollo configuration item
- 03Creating an application or cluster
- 04Publishing or reverting a release
MCP support
The MCP server exposes Apollo open-platform operations as tools for compatible clients such as Cursor, Trae, and Claude Desktop. It connects to a configured Apollo Portal using its URL and token.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEApollo MCP Server
Apollo 配置中心的 MCP (Model Context Protocol) 服务,使大语言模型能够通过配置的 Apollo 地址和 Token 对 Apollo 进行查询和操作。支持 Cursor、Trae、Claude Desktop 等 MCP 客户端。
功能
基于 Apollo 开放平台接口文档 实现以下能力:
- 应用与集群:list_apps、get_app_env_clusters、get_cluster、create_cluster
- 命名空间:list_namespaces、get_namespace、create_namespace、get_namespace_lock
- 配置项:list_items、get_item、create_item、update_item、delete_item
- 发布与回滚:get_latest_release、publish_release、rollback_release
- 应用创建:create_app
前提条件
- Apollo Portal 已部署并可访问
- 在 Portal 的
http://{portal_address}/open/add-consumer.html创建第三方应用并获取 Token - 在
http://{portal_address}/open/manage.html为 Token 绑定可操作的 Namespace
具体可参考官方指引: https://www.apolloconfig.com/#/zh/portal/apollo-open-api-platform
安装
从 PyPI 安装(推荐)
pip install apollo-mcp-server
或使用 uvx 无需安装即可运行:
uvx apollo-mcp-server --url http://your-apollo:8070 --token your_token
开发模式(从源码安装)
pip install -e .
# 或
uv pip install -e .
配置
使用方式
apollo-mcp-server --url http://your-apollo-portal:8070 --token your_open_api_token
--url为 Apollo Portal 根地址(不含/openapi/v1/后缀),如http://localhost:8070。
或
python -m mcp_server_apollo --url http://your-apollo-portal:8070 --token your_open_api_token
Cursor / Trae / Claude Desktop 配置
在 ~/.cursor/mcp.json(Cursor)、Trae 或 claude_desktop_config.json(Claude)中添加:
{
"mcpServers": {
"apollo": {
"command": "uvx",
"args": [
"apollo-mcp-server",
"--url",
"http://your-apollo-portal:8070",
"--token",
"your_open_api_token"
]
}
}
}
也可通过环境变量配置(需 apollo-mcp-server >= 1.0.0):
{
"mcpServers": {
"apollo": {
"command": "uvx",
"args": ["apollo-mcp-server"],
"env": {
"APOLLO_URL": "http://your-apollo-portal:8070",
"APOLLO_TOKEN": "your_open_api_token"
}
}
}
}
开发
# 安装依赖
pip install -e .
# 本地运行(无需安装,从项目目录)
PYTHONPATH=src python -m mcp_server_apollo --url http://localhost:8070 --token your_token
# 或安装后直接运行
apollo-mcp-server --url http://localhost:8070 --token your_token
许可证
MIT License
Comments
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.