What does NATS MCP toolbox do?
It provides CLI tools to expose MCP tools as NATS microservices, allowing local agents to discover and invoke them over NATS.
@hofer
基本信息
This is a collection of cli tools to expose MCP tools via NATS microservices. It can be used either standalone (exposing existing MCP Servers via NATS) or as library in Go to expose functions as tools.
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。
A collection of CLI tools that expose MCP (Model Context Protocol) tools via NATS microservices. It can be used standalone to expose local or existing MCP servers over NATS, or as a Go library to expose functionality as tools.
Run ./nats-mcp tool --url <nats-server> --command <mcp-server-binary> [args] to expose an existing MCP server via NATS. Use ./nats-mcp client list --url <nats-server> to list available tools. Configure a local agent by adding ./nats-mcp server --url <nats-server> to your MCP config. The NATS_URL environment variable sets the default NATS server URL.
NATS_URL environment variable for default URLsIt provides CLI tools to expose MCP tools as NATS microservices, allowing local agents to discover and invoke them over NATS.
Run the command: `./nats-mcp tool --url <nats-url> --command <path-to-mcp-server> [args]`.
Use: `./nats-mcp client list --url <nats-url>`.
Add `./nats-mcp server --url <nats-url>` to your MCP client configuration so the agent can connect to NATS‑exposed tools.
A NATS server and the compiled `nats-mcp` binary. The `NATS_URL` environment variable is used as a default for the `--url` parameter.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.
CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
评论