Remote Terminal MCP
Remote Terminal MCP is a MCP server that provides a shared Linux SSH terminal with AI and user control plus dual-stream visibility.
About
Remote Terminal MCP is a stdio Model Context Protocol server that wraps a complete SSH terminal experience for Linux hosts, designed so an AI agent and a human operator can share control with dual-stream visibility. developers who run their own VPS, staging boxes, or small Kubernetes nodes often paste fragile command sequences into chat; this server instead exposes terminal semantics through MCP tools while anchoring state under REMOTE_TERMINAL_ROOT for configuration and a local database. It suits incident response, log investigation, and careful production changes where you still want to watch every keystroke. Install the PyPI identifier remote-terminal-mcp at version 1.3.3 and point your Claude Code or Cursor MCP config at the stdio entrypoint. Treat SSH credentials and sudo scope as high risk: the MCP integrates the terminal, it does not replace your hardening, backups, or change-management discipline.
- PyPI package remote-terminal-mcp (published version 1.3.3) with stdio transport
- Full Linux SSH terminal usable by both the human and the AI
- Dual-stream visibility so user and agent see terminal output together
- Requires REMOTE_TERMINAL_ROOT for config files and local database
- stdio MCP—runs locally alongside your agent client
Remote Terminal MCP by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --env REMOTE_TERMINAL_ROOT=YOUR_REMOTE_TERMINAL_ROOT remote-terminal-mcp -- uvx remote-terminal-mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | remote-terminal-mcp |
|---|---|
| Transport | STDIO |
| Auth | Required |
What it does
Give your agent a governed SSH terminal on Linux servers with shared visibility between you and the model.
Who is it for?
Best when you SSH into Linux servers daily and want MCP-governed terminal access next to Claude Code or Cursor.
Skip if: Windows-only local dev with no SSH targets, or teams that forbid agents from touching production shells.
What you get
After install and REMOTE_TERMINAL_ROOT setup, your agent can execute SSH-backed terminal workflows while you retain shared visibility on the session stream.
- MCP-exposed SSH terminal session on Linux servers
- Dual-stream output visible to user and agent
- Persistent config and database under REMOTE_TERMINAL_ROOT
By the numbers
- Package version 1.3.3 on PyPI (identifier: remote-terminal-mcp)
- Transport: stdio
- Required env: REMOTE_TERMINAL_ROOT
Recommended MCP Servers
0piFree, 2hr expiry agent storage to cache contexts, bridge workflows, or dump data.
100Hires AI ATS & Recruitment SoftwareOfficial 100Hires MCP: AI ATS & Recruitment Software for candidates, jobs, applications, interviews.123elec McpInterface MCP officielle du site marchand 123elec, catalogue, stock, panier, commandes.
1stayHotel booking MCP server.2
2D Assets MCPMCP server for generating advanced mock 2D PNG assets for game prototypes.43D MeshWeaverMesh spatial optimizer reducing geometric overhead in 3D assets.How it compares
SSH terminal MCP with dual-stream control, not a cloud GPU panel or static documentation skill.
FAQ
Who is Remote Terminal MCP for?
Developers and small teams who operate Linux servers over SSH and want their coding agent to run terminal commands with explicit shared visibility.
When should I use Remote Terminal MCP?
Use it during operate-phase infra tasks—triaging outages, tailing logs, applying hotfixes, or validating deploys on remote hosts—when a real terminal beats isolated tool stubs.
How do I add Remote Terminal MCP to my agent?
Install remote-terminal-mcp from PyPI (1.3.3), set REMOTE_TERMINAL_ROOT to a directory for config and database, and register the stdio server in your MCP client configuration.