termcp

Name: termcp
Author: open-mcp-ai

Local

github.com/open-mcp-aiDeveloper Tools60Updated 2d ago

Repository

About termcp

termcp exposes a terminal interface to AI agents, enabling local and SSH-based host work. It dynamically loads MCP servers and skills while keeping a single MCP tool exposed.

Key features

01Operate terminals locally and over SSH
02Install and call MCP servers dynamically
03Write and hot-load MCP servers
04Expose one MCP tool regardless of loaded servers
05Collaborate through a shared web terminal UI

Use cases

01Manage remote hosts with human-approved SSH access
02Install MCP servers during an agent session
03Create and load a custom MCP server at runtime
04Collaborate with an agent in the same terminal

MCP support

termcp is an MCP server that exposes terminal capabilities through one tool. It can install and invoke other MCP servers dynamically, including across machines over SSH.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config

{
  "mcpServers": {
    "open-mcp-ai-termcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/open-mcp-ai/termcp:0.2.8"
      ]
    }
  }
}

Run commanddocker run -i --rm ghcr.io/open-mcp-ai/termcp:0.2.8

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages

ocighcr.io/open-mcp-ai/termcp:0.2.8Streamable HTTP

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

header banner

⚡ Termcp

English | 中文

divider

Termcp: the final MCP | Terminus MCP

With Termcp:

An AI can install and use any number of MCP servers, dynamically, at run time.
An AI can write its own MCP server and hot-load it.
An AI can use SSH to manage hosts, approved and collaborated on by a human.
An AI can install and call MCP servers across machines over nothing but SSH.

Exactly one tool is exposed. Built on the Termcp protocol (Terminalization Model Context Protocol): loading more MCP servers and skills does not grow the context.

A single dependency-free binary (10 MB+), cross-platform, with a WYSIWYG web UI where a human and an AI share the same terminals and collaborate.

Install 80+ MCP servers and skills.

Host management.

Install

0 · AI install

Install npx -y @open-mcp-ai/termcp daemon stdio as an MCP named termcp.

Copy this to the AI.

1 · One command per agent

Agent	Command
Claude Code	`claude mcp add termcp -- npx -y @open-mcp-ai/termcp daemon stdio`
Codex	`codex mcp add termcp -- npx -y @open-mcp-ai/termcp daemon stdio`
Gemini CLI	`gemini mcp add termcp npx -- -y @open-mcp-ai/termcp daemon stdio`

2 · Config file

{
  "mcpServers": {
    "termcp": {
      "command": "npx",
      "args": ["-y", "@open-mcp-ai/termcp", "daemon", "stdio"]
    }
  }
}

Other install methods — npm / Go / Docker / prebuilt binary

	Command
npm	`npm i -g @open-mcp-ai/termcp` — installs a `termcp` command; with it, drop `npx -y @open-mcp-ai/termcp` from every snippet above and use `termcp`. Wrapper: open-mcp-ai/Termcp-npm.
Go	`go install github.com/open-mcp-ai/termcp@latest` — `GOPROXY=https://goproxy.cn,direct` in mainland China; also usable as a module (`go get github.com/open-mcp-ai/termcp`).
Docker	`docker run -d --name termcp -p 18765:18765 -v termcp-data:/home/termcp -e TERMCP_AUTH_TOKEN=change-me-to-a-long-random-secret ghcr.io/open-mcp-ai/termcp:latest termcp --no-internal --host 0.0.0.0 --port 18765`
Binary	Prebuilt releases — `linux` / `darwin` / `windows` on `amd64` / `arm64`, one static file each.

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.

HTTP transport, when an instance is already answering somewhere (npx -y @open-mcp-ai/termcp):

{
  "mcpServers": {
    "termcp": {
      "type": "http",
      "url": "http://localhost:18765/stream"
    }
  }
}

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 <token>"}.

Docs


`docs/cli.md`	Every flag and subcommand, capability gates, authentication.
`docs/clients.md`	All four entrances end to end: MCP transports, the stdio bridge, authentication, REST examples, and the one-tool surface.
`docs/deploy.md`	Docker, multi-stage builds, Compose, pure-API build.
`docs/protocol.md`	`TERM/1` specification: wire format, status codes, headers, the 19 directives, the three gates.
`docs/capabilities.md`	The full capability surface and the security model.
`docs/api.md`	REST endpoints, WebSocket frames, locator resolution.
`docs/capabilities.md`	Full capability surface and the security model.
`docs/architecture.md`	Session kernel, entrances, storage.
`docs/design/`	Design records: Web UI, resource model, session storage, font stack, mobile terminal.
`CHANGELOG.md`	Release notes.

Benchmark

Comming Soon

Functional security testing

Comming Soon

Star History

License

Released under the MIT License. Thanks to friends in the linux.do community for the discussions, feedback, and support.

footer

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

Read the getting-started guide

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.