
Interminal
io.github.QiuwenZhengPublished by GitHub account QiuwenZhengv1.0.4Updated Oct 24, 2026
Lightweight MCP server providing terminal access (SSH & local shells) for AI assistants.
Overview
Local MCP server that gives an AI assistant terminal access, running commands in local shells or over SSH, including interactive and long-running ones.
- What you can do
- Connect to SSH servers and open sessions with a session ID and welcome banner
- Run commands locally or over SSH, returning output or a partial status with a command ID
- Poll running commands for new output without sending input
- Send text input to a command waiting at a prompt
- Send control keys such as ctrl+c, ctrl+z, arrow keys and function keys
- Disconnect SSH sessions and release their resources
- When to use it
- Useful when an assistant should run shell commands on the user's machine or on remote hosts over SSH, especially for interactive prompts, long-running processes, or multi-step workflows that need a terminal multiplexer for persistent state.
- Requirements
- Runs as a local process over stdio; needs Python 3.11 or newer, launched via uvx or pip install of the mcp-interminal package. SSH access and credentials for remote hosts are supplied through the commands themselves. Optional extras add Windows PTY support and ANSI rendering.
Installation
In SourceWeft
- Open Interminal in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Interminal
Lightweight MCP server that gives AI assistants terminal access — SSH and local shells — with support for interactive and long-running commands.
Installation
Requires Python ≥ 3.11.
MCP Client Configuration
Claude Desktop (claude_desktop_config.json):
Cursor / other clients: same command + args format above.
Tools
Persistent State
Each execute call runs in an isolated channel — there is no persistent shell between calls. For simple tasks, chaining with && works.
For multi-step workflows (project development, debugging, deployment), a terminal multiplexer (like Zellij) provides persistent state that survives across calls. The AI agent can create a persistent session where cd, environment variables, virtual environments, and long-running processes carry over naturally.
Key Behaviors
- Stateless execute — each call is an isolated channel;
cd /foodoes not persist. Simple tasks: chain with&&. Multi-step workflows: use a terminal multiplexer. - Long-running commands return
status="partial"with acommand_id; poll withread_outputor send input withrespond - SSH PTY is 500×200 xterm-256color so multiplexer sessions render at your actual terminal size
Optional Dependencies
Source: README.md at commit ed6d78d
Tools
0Version history
1- v1.0.4LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts