Unterm MCP server
The terminal AI agents can drive: spawn panes, run commands, read screens, scrolling screenshots.
13 stars
Reviews
Write oneNobody has reviewed Unterm yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Unterm tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualityno auth information5/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
How Unterm compares
Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 65/100
- higher than 15% of 1,299 Productivity servers
- GitHub stars
- 13
- more than 80% of 854 Productivity servers
Install Unterm in Claude Code, Cursor or VS Code
The registry entry has no remote endpoint or installable package.
What the publisher says
From the Unterm repository's README, as published. We do not edit it. Read it on GitHub
Unterm
The terminal AI agents can drive.
Cross-platform terminal (macOS / Linux / Windows) built on Unterm's native next-core terminal engine, with one design bet: the terminal itself is controllable from the outside by any AI agent over MCP. Claude Code, Codex, Gemini CLI, Cursor, Aider, your own scripts — they all get the same JSON-RPC surface (149 authenticated methods plus auth.login) to spawn shells, run commands, read pane state, capture screenshots, change settings, and record sessions.
Since v0.68 the terminal is also something an orchestrator can govern rather than merely call: it publishes what it can do and how dangerous each capability is, works under leases that expire and cannot be replayed, keeps agents inside workspaces that cannot see each other, and can hand you an evidence bundle for a task that somebody who was not there can verify.
Since v0.55 the relationship runs both ways: agents drive the terminal from outside, and the terminal is an Agent Cockpit for the agents running inside it — live per-pane agent state, a waiting-first Inbox, fleets of N agents on one task in N isolated git worktrees, and a Review page to diff / merge / roll back what they produced.
The other 2026 terminals each pick a different side: Warp embeds AI inside a closed cloud (Oz), Ghostty stays out of your way and lets you bring your own tools, iTerm2 is Mac-only. Unterm picks the third side — terminal as MCP-controllable surface, deliberately keep AI generation out of the terminal, let external agents grip it through the API, and give the human one cockpit to run them all from.
Practical implications:
no cloud dependency for core operation. Proxy settings auto-detect the system by default and also support explicit HTTP/SOCKS overrides, node pools, rotation, and Clash/mihomo controllers. Finder integration on macOS uses the native Finder right-click extension and Services.
- Every Unterm window starts a local MCP server (line-delimited JSON-RPC over TCP) and a local HTTP settings server (Web Settings page) on auto-allocated ports. Both are auth-token gated, both are 127.0.0.1-only, no cloud round trip.
- Settings live in the browser, not the terminal. Cell-grid TUIs can't deliver modern form UX (no proper text inputs, no live preview, no color picker). The in-terminal ▼ menu holds quick actions and links out to the Web Settings page — configuration itself happens in the browser.
- 9 languages out of the box: en / 简体中文 / 繁體中文 / 日本語 / 한국어 / Deutsch / Français / Italiano / हिन्दी. Auto-detects from system locale, can be overridden in Web Settings or via unterm-cli lang set .
- Multi-instance discovery: every running Unterm process owns one NATO-named instance (alpha, bravo, charlie…) and writes its ports + auth token to ~/.unterm/instances/.json. Agents that drive several windows at once enumerate that directory.
- Cross-platform parity is a correctness property: if a feature works on Windows but bails on macOS or Linux, that's a bug, not "not supported yet."
- Subtraction over decoration: no AI chat overlay inside the terminal and
The GUI and terminal runtime now use Unterm's native next-core engine. The repository still carries selected upstream components and attribution where they remain dependencies, but WezTerm mux/window state is no longer the product kernel.
Agent Cockpit
Run Claude Code, Codex, Gemini CLI, or Aider in any pane and Unterm sees them — no configuration, no wrapper. Five pillars, all local:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Unterm: common questions
- Is Unterm MCP server safe?
- With care: it is graded C, so read the findings first (65/100). Read the Unterm safety report
- Does Unterm need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Unterm maintained?
- The last commit was 41 days ago (2026-09-24). The latest release is v0.57.4.
- What can I use instead of Unterm?
- Servers from other publishers that do the same job: DOMShell MCP server, iPhone Use MCP server and Renforge MCP server.
- How does Unterm compare with other Productivity MCP servers?
- safety score 65/100 (higher than 15% of 1,299 Productivity servers); github stars 13 (more than 80% of 854 Productivity servers). Full comparison.
Alternatives to Unterm
Same job from other publishers: the closest match first, then the best rated.
DOMShellDrive Chrome with filesystem commands (ls, cd, grep, click, type). One MCP tool, multi-agent.not reviewedGrowingA
iPhone UseDrive a real iPhone from a Mac: read the screen as text, tap, type, scroll, replay saved flows.not reviewedGrowingB- RenforgeInspect, drive and debug a running Ren'Py game: state, screenshots, guarded clicks, saves, builds.not reviewedGrowingA
- ArgentDrive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agentnot reviewedWidely usedA
- gflow-cliDrive Google Flow from an agent: Veo video and Imagen image generationnot reviewedEstablishedA