// SCAN REPORT

Terminal Guardian

25 tools. 8 can modify or destroy data without limits.

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

Last updated: 12 Aug 2026

8 can modify or destroy data

17 read-only

25 tools total

Community server · catalogue entry checked 02/08/2026

How to control Terminal Guardian ↓

TOOL MAP

What Terminal Guardian exposes to your agents

Read (17) Write / Execute (6) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Terminal Guardian tools

Destructive · High kill_process Killing a process is irreversible — once terminated, any unsaved state, in-flight work, or transient data is lost and cannot be recovered. Execute · High docker_exec This tool allows running arbitrary commands within Docker containers, which can have wide-ranging side effects depending on what commands are executed. Execute · High run_command This tool executes arbitrary shell commands, which is the defining characteristic of the Execute category. Execute · High ssh_exec This tool enables execution of shell commands on remote servers, which is the definition of Execute category.

8 of Terminal Guardian's 25 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Terminal Guardian

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

Deny destructive operations

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

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

Rate limit write operations

{
  "apply_template": {
    "limits": [
      {
        "counter": "apply_template_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_command": {
    "limits": [
      {
        "counter": "analyze_command_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 Terminal Guardian — 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 TERMINAL GUARDIAN →

Instant setup, no code required.

FULL CATALOGUE

All 25 Terminal Guardian tools

DESTRUCTIVE 1 tools

Destructive kill_process Terminate a process by PID. Uses SIGTERM by default (graceful). SIGKILL requires confirmed=true. System proces

EXECUTE 5 tools

Execute docker_exec Execute a command inside a running Docker container. Requires confirmed: true. Output capped at 512KB. Execute ping Ping a host to check reachability and measure round-trip latency. Private/loopback addresses are blocked by de Execute run_command Execute a shell command in a secure sandboxed environment with risk analysis, timeout enforcement, and output Execute ssh_exec Execute a shell command on a remote server via SSH. Uses the same risk analysis engine as local execution. Req Execute ssh_test Test SSH connectivity to a configured profile. Returns latency and server version.

WRITE 1 tools

Write apply_template Scaffold a new project from a template. Creates files and directories in the target path within the workspace.

READ 17 tools

Read analyze_command Analyze a shell command for safety risks without executing it. Returns risk level (SAFE/WARNING/DANGEROUS/BLOC Read dns_lookup Resolve a hostname to IP addresses using DNS. Read docker_logs Retrieve logs from a Docker container. Read docker_ps List Docker containers with their status, image, and port information. Read docker_stats Get real-time resource usage statistics for a Docker container. Read get_env Read environment variables with automatic secret masking. Secrets (tokens, passwords, keys) are shown as maske Read git_diff Show Git diff for working tree or staged changes. Read git_log Show Git commit history with author, date, and message. Read git_status Get the current Git repository status including staged, unstaged, and untracked files. Read git_suggest_commit Generate AI-powered commit message suggestions from git diff using Claude. Returns conventional commit format Read http_request Make an HTTP/HTTPS request and return status, headers, and body. Only http:// and https:// allowed. Response b Read list_files List files and directories within the workspace. Access is restricted to allowed paths. Read list_processes List running system processes with CPU, memory usage, and command info. Supports filtering by name and sorting Read list_templates List available workspace templates for scaffolding new projects. Includes Node.js, TypeScript, Python, FastAPI Read read_file Read the contents of a file within the workspace. Access is restricted to allowed paths and file size limits. Read search_files Search for text across files in the workspace. Returns matching lines with context. Read ssh_list_profiles List all configured SSH profiles with their host, port, username, and auth method.

OTHER 1 tools

Other hello Say hello

EXPLORE

Related servers

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

FAQ

Questions about Terminal Guardian

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

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

How do I prevent bulk modifications through Terminal Guardian? +

The Terminal Guardian server has 1 write tools including apply_template. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Terminal Guardian.

How many tools does the Terminal Guardian MCP server expose? +

25 tools across 3 categories: Execute, Read, Write. 17 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Terminal Guardian? +

Register the Terminal Guardian 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 Terminal Guardian tool call.

Deterministic rules across all 25 Terminal Guardian tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TERMINAL GUARDIAN →

Instant setup, no code required.

25 Terminal Guardian tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Terminal Guardian's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →