cond_close · TermPipe MCP: Risk & Policy

WHAT IT DOES

What cond_close does on TermPipe MCP

AI agents use cond_close to create or update resources in TermPipe MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TermPipe MCP environment.

WHY IT NEEDS A POLICY

Why cond_close needs a policy

An AI agent can call cond_close faster than any human can review — one bad instruction and it creates or modifies resources in TermPipe MCP by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cond_close Rate-limited

cond_close stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "cond_close": {
      "limits": [
        {
          "counter": "cond_close_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about cond_close

What does the cond_close tool do? +

Close a window by app-id or name (fuzzy match). It is categorised as a Write tool in the TermPipe MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on cond_close? +

Register the TermPipe MCP server in PolicyLayer and add a rule for cond_close: 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 TermPipe MCP. Nothing to install.

What risk level is cond_close? +

cond_close is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit cond_close? +

Yes. Add a rate_limit block to the cond_close 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 cond_close completely? +

Set action: deny in the PolicyLayer policy for cond_close. 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 cond_close? +

cond_close is provided by the TermPipe MCP server (wbind-core/termpipe-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.