GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
作者提供的说明(英文原文)
Reach an MCP server inside your Tailscale tailnet from an agent's sandbox, over stdio.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
TS_AUTHKEY标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"tailnet": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"TS_AUTHKEY",
"ghcr.io/zedong-peng/tailnet-mcp:v0.3.0",
"-url",
"your-value",
"-hostname",
"tailnet-mcp"
],
"env": {
"TS_AUTHKEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add tailnet --env TS_AUTHKEY=your-value -- docker run -i --rm -e TS_AUTHKEY ghcr.io/zedong-peng/tailnet-mcp:v0.3.0 -url your-value -hostname tailnet-mcp运行前请先填写空着的值。
这个服务器需要在启动命令中填入值,请复制设置后自行填写。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"tailnet": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"TS_AUTHKEY",
"ghcr.io/zedong-peng/tailnet-mcp:v0.3.0",
"-url",
"your-value",
"-hostname",
"tailnet-mcp"
],
"env": {
"TS_AUTHKEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器需要在启动命令中填入值,请复制设置后自行填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"tailnet": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"TS_AUTHKEY",
"ghcr.io/zedong-peng/tailnet-mcp:v0.3.0",
"-url",
"your-value",
"-hostname",
"tailnet-mcp"
],
"env": {
"TS_AUTHKEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
注册名称已通过 GitHub 账户 zedong-peng 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:TS_AUTHKEY
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.3.0)于4天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Docker。
同一分类中有:GitHub, Desktop Commander, Cloudflare MCP
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
A stdio MCP server that forwards everything to a Streamable HTTP MCP server inside your tailnet.
Hosted agents (Grok, cloud coding agents, sandboxed assistants) usually take MCP servers two ways. By URL: the vendor's servers connect, so your server has to be on the public internet. By command: the agent starts a process on its own computer, but that computer is not in your tailnet and you can't run tailscaled there (no root, no TUN). tailnet-mcp is the command: it embeds a Tailscale node (tsnet), joins your tailnet as a tagged device and bridges stdio to the server. Your server stays behind tailscale serve, never on the internet.
agent ──stdio──▶ tailnet-mcp (tag:agent) ══tailnet══▶ tailscale serve ──▶ MCP server on 127.0.0.1
Download a static binary for linux or darwin, amd64 or arm64, from Releases and check it against SHA256SUMS. Or build it yourself:
CGO_ENABLED=0 go install github.com/zedong-peng/tailnet-mcp@latest
Or run the image ghcr.io/zedong-peng/tailnet-mcp with a volume on /home/nonroot/.local/state/tailnet-mcp. It is also listed in the MCP Registry as io.github.zedong-peng/tailnet-mcp.
tailscale serve --bg --https=8443 --set-path=/$(openssl rand -hex 16) http://127.0.0.1:8080/mcp
TS_AUTHKEY=tskey-auth-... tailnet-mcp -hostname my-agent -url https://server.tailnet.ts.net:8443/<path> -check
-check connects, prints the server's tools on stderr and exits. The node key is kept in -state (default ~/.local/state/tailnet-mcp/ ); keep it on persistent storage. Tagged nodes don't expire, so the key is not needed again.
tailnet-mcp -hostname my-agent -url https://server.tailnet.ts.net:8443/<path>
Each process is its own tailnet node. For a second server, run a second process with a different -hostname.
The agent reads untrusted input (web pages, mail), so assume it can be talked into anything its tools allow. Three layers, none of which rely on the agent behaving:
"grants": [
{"src": ["tag:my-agent"], "dst": ["server"], "ip": ["tcp:8443"]}, ], "tests": [ {"src": "tag:my-agent", "accept": ["server:8443"], "deny": ["server:22", "server:443"]}, ],
Grants that allow everything ("src": ["autogroup:member"], "dst": ["*"]) don't cover tagged devices, so that one grant is all the tag gets.
tailscale serve --set-path answers only on the secret path; any other path on the port is a 404. Other devices in the tailnet can't use the server by guessing the port.initialize and resends the request. The client doesn't notice.DELETE. Logs go to stderr; stdout carries only MCP frames. -v adds tsnet's own logs.Not supported: the optional GET stream that lets a server send messages outside a response. Servers answer each request in its own response, as almost all tool servers do.
go test -race ./...
CGO_ENABLED=0 go build -trimpath -ldflags="-s -w" .
Tagging v* publishes the four binaries, the image and the registry entry.