jewei-mcp-nacos
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., "@jewei-mcp-nacos Show me the user-service.yml configuration from the dev namespace"
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.
jewei-mcp-nacos
Nacos MCP Server - 让 AI 助手能够查询和管理 Nacos 配置。
支持 Nacos 1.x/2.x/3.x 版本。
快速开始
Claude Code
在项目 .mcp.json 或全局 ~/.claude.json 中添加:
{
"mcpServers": {
"nacos": {
"type": "stdio",
"command": "uvx",
"args": ["jewei-mcp-nacos"],
"env": {
"NACOS_HOST": "localhost",
"NACOS_API_PORT": "8848",
"NACOS_CONSOLE_PORT": "8080",
"NACOS_USERNAME": "nacos",
"NACOS_PASSWORD": "your-password",
"NACOS_NAMESPACE": "dev",
"NACOS_VERSION": "3",
"NACOS_READ_ONLY": "false"
}
}
}
}Cursor
在 ~/.cursor/mcp.json 中添加:
{
"mcpServers": {
"nacos": {
"command": "uvx",
"args": ["jewei-mcp-nacos"],
"env": {
"NACOS_HOST": "localhost",
"NACOS_API_PORT": "8848",
"NACOS_CONSOLE_PORT": "8080",
"NACOS_NAMESPACE": "dev",
"NACOS_VERSION": "3",
"NACOS_READ_ONLY": "false"
}
}
}
}OpenCode
在 ~/.opencode/opencode.json 中添加:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"nacos": {
"type": "local",
"command": ["uvx", "jewei-mcp-nacos"],
"enabled": true,
"environment": {
"NACOS_HOST": "localhost",
"NACOS_API_PORT": "8848",
"NACOS_CONSOLE_PORT": "8080",
"NACOS_NAMESPACE": "dev",
"NACOS_VERSION": "3",
"NACOS_READ_ONLY": "false"
}
}
}
}Claude Desktop
在 claude_desktop_config.json 中添加:
{
"mcpServers": {
"nacos": {
"command": "uvx",
"args": ["jewei-mcp-nacos"],
"env": {
"NACOS_HOST": "localhost",
"NACOS_API_PORT": "8848",
"NACOS_CONSOLE_PORT": "8080",
"NACOS_USERNAME": "nacos",
"NACOS_PASSWORD": "your-password",
"NACOS_NAMESPACE": "dev",
"NACOS_VERSION": "3",
"NACOS_READ_ONLY": "false"
}
}
}
}Related MCP server: agileconfig-mcp-server
环境变量
变量 | 说明 | 默认值 |
| Nacos 服务地址 |
|
| API 端口(仅 v1/v2 使用,v1/v2 必填) |
|
| API 端口(用于登录,仅 v3 使用,v3 必填) |
|
| Console 端口(用于配置操作,仅 v3 使用,v3 必填) |
|
| 用户名(可选) | - |
| 密码(可选) | - |
| 默认命名空间 ID(当 NACOS_VERSION=1 时表示 Nacos 的命名空间 ID 字段) |
|
| Nacos 版本(1/2/3),默认 3 |
|
| 只读模式,禁用发布功能 |
|
可用工具
工具 | 说明 |
| 获取配置内容 |
| 发布/更新配置(只读模式下不可用) |
提示示例
配置好后,你可以这样和 AI 对话:
查询配置:
帮我获取 Nacos 中 dataId 为 "application.yaml" 的配置查看 nacos 里 user-service.yml 的配置内容,namespace 是 dev获取 gateway 的配置,分组是 PROD_GROUP发布配置:
把下面这段配置发布到 Nacos,dataId 是 "redis.yaml":
server:
port: 6379更新 user-service 的配置,把数据库端口改成 3307只读模式
设置 NACOS_READ_ONLY=true 可以禁用发布功能,只允许查询配置。适合生产环境使用。
{
"env": {
"NACOS_READ_ONLY": "true"
}
}License
MIT
Available Tools
2 toolsnacos_get_configBRead-onlyIdempotent
获取 Nacos 配置内容。
从 Nacos 配置中心获取指定的配置内容。
参数:
params: 包含以下内容的验证输入参数:
- data_id: 配置 ID
- group_name: 配置分组,默认 DEFAULT_GROUP
- namespace_id: 命名空间 ID,可选
- response_format: 输出格式,markdown 或 json
返回:
配置内容(Markdown 或 JSON 格式)
Inputs: params (required). Returns: result
nacos_publish_configAIdempotent
发布 Nacos 配置。
创建新配置或更新已有配置。
参数:
params: 包含以下内容的验证输入参数:
- data_id: 配置 ID
- group_name: 配置分组,默认 DEFAULT_GROUP
- namespace_id: 命名空间 ID,可选
- content: 配置内容
- config_type: 配置类型,默认 yaml
- desc: 配置描述,可选
返回:
发布结果
Inputs: params (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one retrieves configuration content from Nacos, while the other publishes/updates configuration. There is no overlap in functionality, and the descriptions clearly differentiate between read and write operations.
Both tools follow a consistent naming pattern: 'nacos_' prefix followed by verb_noun (get_config, publish_config). This pattern is uniform across all tools, making them easily identifiable and predictable.
With only two tools, this server feels severely under-scoped for managing a configuration system like Nacos. Essential operations like listing configurations, deleting configurations, or monitoring changes are missing, making the toolset incomplete for typical configuration management workflows.
The toolset covers basic get and publish operations but lacks critical CRUD/lifecycle coverage for a configuration management system. There are no tools for listing available configurations, deleting configurations, or handling configuration versioning, which are standard needs in this domain.
Maintenance
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
An MCP server that integrates with Discord to provide AI-powered features.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Related MCP Servers
AlicenseAqualityDmaintenanceA server that enables interaction with Nacos service discovery and configuration management through Large Language Models, providing read-only access to namespaces, services, and configurations.1112Apache 2.0- AlicenseAqualityDmaintenanceMCP server that exposes all AgileConfig RESTful APIs as tools, enabling AI assistants to manage configuration, applications, users, nodes, and more via natural language.367 npmMIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI assistants to search, read, and manage files across multiple cloud drives (Baidu, Aliyun, 115, OneDrive, Quark) through a unified interface.10 npmMIT
- AlicenseAqualityCmaintenanceEnables AI assistants to query and manage Nacos configurations, supporting Nacos 1.x/2.x/3.x with multiple transport protocols.71MIT