Just A Nacos
FreeNot checkedA local MCP server for Nacos 3.0.x — exposes namespace listing, config reading, and full-text config search as tools for AI agents (Kiro, Claude Desktop, Cursor
About
A local MCP server for Nacos 3.0.x — exposes namespace listing, config reading, and full-text config search as tools for AI agents (Kiro, Claude Desktop, Cursor). Built with Python + FastMCP.
README
Read your Nacos 3.0.x configuration directly from your AI agent.
No official Nacos MCP exists for v3 — this fills that gap.
Read-only by design. All tools are read operations only. Write operations will never be added — an agent writing config with a wrong namespace or at the wrong moment can cause production-level incidents. Just because we can doesn't mean we should.
What it does
Once connected, your AI agent (Kiro, Claude Desktop, Cursor, etc.) can:
- List namespaces — see all environments in your Nacos server
- List configs — browse configs in any namespace, with fuzzy filtering by dataId or group
- Get a config — fetch content and full metadata (md5, type, created by, timestamps)
- Search by content — find all configs containing a specific keyword
Requirements
- uv —
brew install uv - Nacos 3.0.x server (tested on 3.0.3)
Setup
1. Clone and install
git clone https://github.com/xingyuli/just-a-nacos-mcp
cd just-a-nacos-mcp
uv sync
2. Add to your AI agent
Add this to your MCP config file (.kiro/settings/mcp.json for Kiro, or ~/Library/Application Support/Claude/claude_desktop_config.json for Claude Desktop):
{
"mcpServers": {
"nacos": {
"command": "uv",
"args": [
"--directory", "/path/to/just-a-nacos-mcp",
"run", "nacos_mcp_server.py"
],
"env": {
"NACOS_URL": "http://your-nacos-host:8848",
"NACOS_AUTH": "true",
"NACOS_USERNAME": "your-username",
"NACOS_PASSWORD": "your-password"
}
}
}
}
If your credentials are already exported in
~/.zprofileor~/.zshrc, you can reference them directly:"NACOS_URL": "${NACOS_URL}", "NACOS_USERNAME": "${NACOS_USERNAME}", "NACOS_PASSWORD": "${NACOS_PASSWORD}"
3. Restart your agent and start asking questions like:
- "List all namespaces on Nacos"
- "Show me all configs in the dev namespace"
- "Get the content of datasource.yaml in group DEFAULT_GROUP"
- "Which configs contain the word 'redis'?"
Configuration
| Variable | Required | Default | When to set |
|---|---|---|---|
NACOS_URL |
Yes | http://localhost:8848 |
Always. Point this at the console HTTP port (default 8848) — not the gRPC port (default 9848). See note below. |
NACOS_AUTH |
No | false |
Set to true if your Nacos server has authentication enabled (nacos.core.auth.enabled=true). |
NACOS_USERNAME |
No | nacos |
Required when NACOS_AUTH=true. |
NACOS_PASSWORD |
No | nacos |
Required when NACOS_AUTH=true. |
NACOS_NAMESPACE |
No | (empty = public) | Optional but recommended if you mostly work in one namespace. When set, all tools default to that namespace without you needing to specify it in every prompt. You can still override it at any time by mentioning a different namespace in your prompt. Leave empty to default to the built-in public namespace. |
Console port vs gRPC port: Every Nacos server (standalone or cluster) exposes two ports. Port
8848(HTTP) serves the web console, REST API, and this MCP server. Port9848(gRPC, offset +1000) is used exclusively by Spring Cloud / SDK clients.NACOS_URLmust point to the HTTP port.
Token refresh
Authentication tokens are cached and refreshed automatically before they expire. No manual intervention needed.
For implementation details, endpoint reference, and contributing guide, see DEVELOPMENT.md.
Install Just A Nacos in Claude Desktop, Claude Code & Cursor
unyly install just-a-nacosInstalls into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.
First time? Get the CLI: curl -fsSL https://unyly.org/install | sh
Or configure manually
Run in your terminal:
claude mcp add just-a-nacos -- uvx --from git+https://github.com/xingyuli/just-a-nacos-mcp just-a-nacos-mcpStep-by-step: how to install Just A Nacos
FAQ
Is Just A Nacos MCP free?
Yes, Just A Nacos MCP is free — one-click install via Unyly at no cost.
Does Just A Nacos need an API key?
No, Just A Nacos runs without API keys or environment variables.
Is Just A Nacos hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Just A Nacos in Claude Desktop, Claude Code or Cursor?
Open Just A Nacos on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Fetch
Web content fetching and conversion for efficient LLM usage.
Roblox Studio
Enables AI coding tools to control Roblox Studio for workspace exploration, instance manipulation, and script management. It provides tools for playtesting, sce
by paralovOpencode Omniroute Plugin
OpenCode plugin for the OmniRoute AI Gateway. Drives dynamic model discovery, /connect auth flow, and multi-instance OmniRoute providers via the official @openc
by GitHub ActionsAWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzMCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
by lastmile-aiSpring AI MCP Client
Provides auto-configuration for MCP client functionality in Spring Boot applications.
mcp.natoma.ai
A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)
MCPHub
Website to list high quality MCP servers and reviews by real users. Also provide online chatbot for popular LLM models with MCP server support.
Compare Just A Nacos with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
