nano-mcp-termux
Zero-dependency, single-file MCP server for AI agents, natively running on Termux (Android), Raspberry Pi, and Linux.
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
uvx nano-mcp-termux==1.1.1Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add io.github.lmeng486-nano-mcp-termux -- uvx nano-mcp-termux==1.1.1在終端機中執行。
{ "mcpServers": { "io.github.lmeng486-nano-mcp-termux": { "command": "uvx", "args": [ "nano-mcp-termux==1.1.1" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
cd /path/to/nano-mcp-termux
python3 nano_mcp_termux.py
docker build -t nano-mcp-termux .
docker run -i --rm nano-mcp-termux
python3 nano_mcp_termux.py --health
This server does not run standalone — it's a sidecar that your AI client connects to via the MCP protocol.
Below are the three most common ways to mount it.
uvx), best for desktop AI clientsuvx nano-mcp-termux
Then add this JSON to your AI client's mcpServers config (see client‑specific notes below):
{
"mcpServers": {
"nano-mcp-termux": {
"command": "uvx",
"args": ["nano-mcp-termux"]
}
}
}
pip installed, or you prefer a direct Python launchpip install nano-mcp-termux
Config snippet for your AI client:
{
"mcpServers": {
"nano-mcp-termux": {
"command": "nano-mcp-termux"
}
}
}
# Clone or download the repo, then:
cd /path/to/nano-mcp-termux
python3 nano_mcp_termux.py
Config snippet for your AI client:
{
"mcpServers": {
"nano-mcp-termux": {
"command": "python3",
"args": ["/full/path/to/nano_mcp_termux.py"]
}
}
}
Tip: after editing the config file, restart your AI client so the new server is detected. If the client supports hot‑reload, you may not need a restart.
protocolVersion (2024-11-05 / 2025-06-18 / 2025-11-25), falls back to highest supporteddevice_status never fails; unavailable inputs are marked, not crashedSIGTERM → SIGKILL), never just the shell/sdcard ↔ /storage/emulated/0 ↔ $HOME/storage/shared, detects noexec mounts, case-insensitive filesystems, and shell-quoting hazardsVersion 1.0.0 ran commands with subprocess.run(..., timeout=...). On timeout,
Python terminates only the direct child — the sh -c wrapper. Anything the
shell had already spawned is reparented to init and survives forever. On
Android that is the exact leak class that trips the Phantom Process Killer
and can get the whole app group killed.
1.1.0 fixes this at the root: commands are spawned with start_new_session=True
and torn down with os.killpg(pgid, SIGTERM) → SIGKILL, so the entire process
tree dies together.
The repository ships a reproducible A/B regression test for it:
python3 test_lifecycle_orphan.py
# current nano_mcp_termux.py leaked_grandchildren=0
# legacy nano_mcp_termux_v10_backup.py leaked_grandchildren=1 <- the bug
# PASS: current server leaves 0 orphaned grandchildren after timeout
python3 test_client.py # 32 protocol / tool / lifecycle assertions
python3 test_lifecycle_orphan.py # orphan-leak A/B regression (1.0.0 vs 1.1.0)
This server is designed to pass Glama introspection checks and serve as a lightweight MCP implementation for mobile and edge devices.
Zero-dependency single-file MCP server for Termux/Android, Raspberry Pi and Linux
{ "mcpServers": { "io.github.lmeng486-nano-mcp-termux": { "command": "uvx", "args": [ "nano-mcp-termux==1.1.1" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Nano MCP Termux 透過 stdio 在本機執行。
上次檢查時間:2026-11-09。 Zero-dependency single-file MCP server for Termux/Android, Raspberry Pi and Linux