// SCAN REPORT

Persistent Terminal MCP Server

10 tools. 7 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

7 can modify or destroy data

3 read-only

10 tools total

Community server · catalogue entry verified 29/06/2026

How to control Persistent Terminal MCP Server ↓

TOOL MAP

What Persistent Terminal MCP Server exposes to your agents

Read (3) Write / Execute (6) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Persistent Terminal MCP Server tools

Destructive · High kill_terminal Killing a terminal session is irreversible — any unsaved work, running processes, or state within that session is permanently lost. Execute · Critical fix_bug_with_codex This tool runs OpenAI Codex CLI in a fully automated, unrestricted mode with no sandboxing and no human approval gate. Execute · High wait_for_output This tool does not retrieve data in a read-only sense; rather, it synchronizes with the execution state of a running terminal session. Execute · High create_terminal Creating a persistent terminal session establishes an execution environment capable of running arbitrary shell commands.

7 of Persistent Terminal MCP Server's 10 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Persistent Terminal MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Persistent Terminal MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "kill_terminal": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Cap read operations

{
  "get_terminal_stats": {
    "limits": [
      {
        "counter": "get_terminal_stats_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Persistent Terminal MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON PERSISTENT TERMINAL →

Instant setup, no code required.

FULL CATALOGUE

All 10 Persistent Terminal MCP Server tools

DESTRUCTIVE 1 tools

Destructive kill_terminal Terminate a terminal session

EXECUTE 6 tools

Execute create_terminal Create a new persistent terminal session Execute create_terminal_basic Create a new persistent terminal session (shell and cwd only). Useful for clients that cannot send env objects Execute fix_bug_with_codex Use OpenAI Codex CLI to automatically fix bugs with FULL SYSTEM ACCESS. WARNING CRITICAL: This tool gives Cod Execute open_terminal_ui Open a web-based terminal management UI in the browser. This provides a visual interface to manage all termina Execute wait_for_output Wait for terminal output to stabilize. Useful after running commands to ensure all output is captured. Execute write_terminal Write input to a terminal session. Commands add a newline by default, but you can disable that for raw control

READ 3 tools

Read get_terminal_stats Get detailed statistics about a terminal session including size, tokens, etc. Read list_terminals List all active terminal sessions Read read_terminal Read output from a terminal session with smart truncation options

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Persistent Terminal MCP Server

Can an AI agent delete data through the Persistent Terminal MCP Server MCP server? +

Yes. The Persistent Terminal MCP Server server exposes 1 destructive tools including kill_terminal. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How many tools does the Persistent Terminal MCP Server MCP server expose? +

10 tools across 4 categories: Destructive, Execute, Read, Write. 3 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Persistent Terminal MCP Server? +

Register the Persistent Terminal MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Persistent Terminal MCP Server tool call.

Deterministic rules across all 10 Persistent Terminal MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PERSISTENT TERMINAL →

Instant setup, no code required.

10 Persistent Terminal MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.