termmirrorSAFE
MCP server giving AI agents real interactive terminal sessions - PTY, TUIs, REPLs, SSH, even another agent's CLI - with a live web view a human can watch and type into
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An MCP server that gives AI agents real interactive terminal sessions — and a live web view where a human can watch those sessions and type into them.
Most agent tooling can only run commands that exit on their own. Anything that prompts, redraws, or waits for a keystroke is out of reach: installers, ssh with a password challenge, pdb, vim, a package manager's configuration screen — and another agent's CLI. termmirror keeps real PTY sessions open so an agent can work them the way a person does, one keystroke at a time, while a human can look over its shoulder and step in when needed.
One agent driving a Claude Code session through termmirror — it accepted the trust prompt, asked a question, and read the answer off the screen. The browser view is live, and typing in it goes straight to the same terminal.
A full-screen TUI under the same tools: the agent opened `vim`, moved to the end of the file, entered insert mode, and typed a line.
Features
- Real PTY sessions. Backed by
node-ptywith a headless terminal emulator holding
screen state. No tmux or other external dependency.
- Built for TUIs. Alternate-screen detection, key encoding for control and navigation
keys, and scrollback that unwraps soft-wrapped lines.
- Reliable waiting.
waitreturns once a program has responded and settled, so the
screen you read reflects your input rather than the state before it.
- Live web view. Any session can be watched in the browser as it runs. Typing in the
page goes straight to the PTY, so a human can take over and hand back.
- Agent-to-agent. Designed so one agent can drive another agent's CLI through a
multi-turn conversation.
- Browser sessions too. The same three properties for a real Chrome window: the agent
drives it by accessibili
f8472c3753e7OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add termmirror -- npx -y [email protected]
{
"mcpServers": {
"termmirror": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (16)
10 read · 5 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
browser_act | read | |
browser_navigate | read | |
browser_open | read | |
browser_snapshot | read | |
browser_tabs | read | |
browser_wait | read | |
create_session | write | |
kill_session | destructive | |
list_sessions | read | |
read_screen | read | |
resize | read | |
send_input | write | |
send_keys | write | |
start_recording | write | |
stop_recording | write | |
wait | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (4)
kill_session
const { version } = createRequire(import.meta.url)("../../package.json") as { version: string };termmirror
@modelcontextprotocol/sdk, @xterm/headless, @xterm/xterm, node-pty, playwright-core, ws, zod, @types/node
Gates applied: no_behavioural_pass.
f8472c3753e7full audit observations/trust-audit/mcp-server/ar9av__termmirror.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | f8472c3753e7 | SAFE | B | 89 | first audit |
Questions
What is the termmirror MCP server?
MCP server giving AI agents real interactive terminal sessions - PTY, TUIs, REPLs, SSH, even another agent's CLI - with a live web view a human can watch and type into
What tools does termmirror expose?
16 in total: 10 read-only, 5 that write, and 1 that can delete or overwrite (kill_session). Every one is listed on this page with its risk.
Is termmirror safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does termmirror need?
No credential environment variables were found in its source, so it appears to need none.
How does termmirror run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as termmirror at 0.2.0.
How current is this page?
The grade is for one exact copy of the source (f8472c3753e7), read on 2026-10-11. The repository is watched and re-audited when it changes.