What are the required dependencies?
Node.js >= 14.0.0 and the NATS CLI (`nats`) installed on the system.
@bmorphism
基本信息
MCP server for NATS messaging system using NATS CLI - enabling AI agents to interact with NATS messaging
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"nats": {
"command": "node",
"args": [
"/path/to/nats-mcp-server/build/index.js"
],
"env": {
"NATS_URL": "nats://localhost:4222"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
NATS MCP Server is a Model Context Protocol server that provides access to NATS, a cloud-native messaging system, through the NATS CLI. It enables AI models to publish, subscribe to, and request-reply over NATS subjects.
Install via npm (npm install @modelcontextprotocol/nats-mcp-server) or build from source. Configure with the NATS_URL environment variable (default nats://localhost:4222). Add the server to your MCP client’s configuration (e.g., Cline or Claude Desktop) and then invoke its tools: publish, subscribe, or request.
Node.js >= 14.0.0 and the NATS CLI (`nats`) installed on the system.
Installation varies by OS: Homebrew on macOS (`brew install nats`), `snap install nats` on Linux, Chocolatey or Scoop on Windows, or build from source with Go.
Set the `NATS_URL` environment variable before starting the MCP server. Default is `nats://localhost:4222`.
Three tools: `publish` (send messages with optional headers, templates, and reply subjects), `subscribe` (receive messages with timeout and count limits), and `request` (send a request and wait for a reply with optional headers).
Yes. When `template: true` is set on `publish`, the message can use functions like `{{Count}}`, `{{Time}}`, `{{Random min max}}`, and others.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
🚀 The fast, Pythonic way to build MCP servers and clients.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
评论