What environment variables are required?
`NATS_URL` (e.g., `nats://localhost:4222`) is required. Optional `NATS_<ACCOUNT>_CREDS` variables hold base64‑encoded credentials for each account (e.g., `NATS_SYS_CREDS`).
@sinadarbouy
基本信息
This project provides a Model Context Protocol (MCP) server for NATS, enabling AI models and applications to interact with NATS messaging systems through a standardized interface. It exposes a comprehensive set of tools for interacting with NATS servers, making it ideal for AI-po
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"nats": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--init",
"-e",
"NATS_URL",
"-e",
"NATS_SYS_CREDS",
"cnadb/mcp-nats",
"--transport",
"stdio"
],
"env": {
"NATS_SYS_CREDS": "<base64 of SYS account creds>",
"NATS_URL": "<nats url>"
}
}
}
}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 is an MCP server that connects AI assistants to the NATS messaging system. It is for developers who want to interact with NATS servers through Model Context Protocol clients.
Install via go install or build from source, then run with required environment variables (NATS_URL, optional NATS_<ACCOUNT>_CREDS). Configure transport (stdio or SSE), log level, and logging format via command line flags.
—
`NATS_URL` (e.g., `nats://localhost:4222`) is required. Optional `NATS_<ACCOUNT>_CREDS` variables hold base64‑encoded credentials for each account (e.g., `NATS_SYS_CREDS`).
The `--transport` flag accepts `stdio` (default) or `sse`. With SSE, the server listens on the address specified by `--sse-address` (default `0.0.0.0:8000`).
Use `--log-level` to set level (`debug`, `info`, `warn`, `error`; default `info`) and `--json-logs` to output logs in JSON format (default `false`).
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.
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
Hindsight: Agent Memory That Learns

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
评论