pty_write · Pty MCP: Risk & Policy

WHAT IT DOES

What pty_write does on Pty

AI agents invoke pty_write to trigger actions in Pty. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why pty_write needs a policy

pty_write sends arbitrary input to an active pseudo-terminal session, which can drive any interactive CLI process. Since the server is designed to execute shell commands, run database migrations, and scaffold projects, writing to a PTY session effectively executes arbitrary commands in that shell. The blast radius is high because an AI agent could send destructive or privileged commands to any running process.

From the tool's definition Send input to a running PTY session... enables agents to autonomously spawn processes, read output, and send inputs for workflows like database migrations and project scaffolding

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pty_write Rate-limited

pty_write stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "pty_write": {
      "limits": [
        {
          "counter": "pty_write_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Pty, so you can run agents against it safely.

FAQ

Questions about pty_write

What does the pty_write tool do? +

Send input to a running PTY session. Returns new output after the input is processed. Use press_enter to submit (default true). It is categorised as a Execute tool in the Pty MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on pty_write? +

Register the Pty MCP server in PolicyLayer and add a rule for pty_write: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Pty. Nothing to install.

What risk level is pty_write? +

pty_write is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit pty_write? +

Yes. Add a rate_limit block to the pty_write rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block pty_write completely? +

Set action: deny in the PolicyLayer policy for pty_write. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides pty_write? +

pty_write is provided by the Pty MCP server (reedm121/pty-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.