最终的 MCP | Terminus MCP
Overview
Built on the (Terminalization Model Context Protocol): loading more MCP servers and skills does not grow the context. where a human and an AI share the same terminals and collaborate. Other install methods — npm / Go / Docker / prebuilt binary The npm wrapper downloads the matching prebuilt binary (override with TERMCP_VERSION, TERMCP_MIRROR, TERMCP_BIN, TERMCP_SKIP_DOWNLOAD). Flags: docs/cli.md. Docker recipes, Compose and a token-free loopback setup: docs/deploy.md. , when an instance is already answering somewhere (npx -y @open-mcp-ai/termcp): Reachable from a client in Docker as http://host.docker.internal:18765/stream (macOS/Windows) or the host's LAN IP; from another container on the same network as http://termcp:18765/stream. Legacy SSE uses http://localhost:18765/sse — only /sse, JSON-RPC goes to /message by itself. With --auth-token, add a bearer header: "headers": {"Authorization": "Bearer "}. Released under the MIT License. Thanks to friends in the linux.
README
View the full README on GitHubInstall
npx -y @open-mcp-ai/termcp daemon stdioConfiguration
{
"mcpServers": {
"termcp": {
"command": "npx",
"args": ["-y", "@open-mcp-ai/termcp", "daemon", "stdio"]
}
}
}