What routers are supported?
AsusWRT and AsusWRT-Merlin routers with SSH access enabled.
@teefloo
基本信息
Model Context Protocol server for secure AsusWRT router administration via SSH. Provides 42+ read-only monitoring tools and guarded mutation tools for managing AsusWRT/Merlin routers
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"asuswrt-mcp": {
"command": "C:\\path\\to\\asuswrt-mcp\\.venv\\Scripts\\python.exe",
"args": [
"-m",
"asuswrt_mcp.server"
],
"env": {
"ASUSWRT_HOST": "192.168.1.1",
"ASUSWRT_SSH_USERNAME": "admin",
"ASUSWRT_SSH_PASSWORD": "your_password"
}
}
}
}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 Model Context Protocol server that provides AI assistants with a secure, controlled interface to monitor and manage AsusWRT and AsusWRT-Merlin routers exclusively over SSH using allowlisted operations.
Install with Python 3.11+, configure the .env file with router SSH credentials, then run python -m asuswrt_mcp.server or configure it in Claude Desktop / Cursor via claude_desktop_config.json. Mutations require setting ASUSWRT_ALLOW_MUTATIONS=true and passing confirm: true.
AsusWRT and AsusWRT-Merlin routers with SSH access enabled.
Python 3.11+ is required, and network connectivity from the MCP client to the router.
Only allowlisted commands are executed via NVRAM and service calls. No arbitrary SSH, firmware operations, factory resets, or bootloader access is allowed.
Set the `ASUSWRT_ALLOW_MUTATIONS=true` environment variable and pass `confirm: true` in each mutation call. Dry-run is also supported with `dry_run: true`.
Clone the repository, create a Python virtual environment, install with `pip install -e .`, copy `.env.example` to `.env`, and configure router credentials.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Verified cyber-physical AI tools. 25 MCP tools, x402-payable on Base.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
Get a second opinion on your code from every coding agent you have. Claude Code, Codex and Grok review each other's diffs and answer each other's questions, even inside a session that's already running. Uses the CLIs you
评论