cond_ocr · TermPipe MCP: Risk & Policy

WHAT IT DOES

What cond_ocr does on TermPipe MCP

AI agents invoke cond_ocr to trigger actions in TermPipe MCP. 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 cond_ocr needs a policy

This tool executes a sequence of dependent operations: window capture, OCR inference via an external service (qwen-vl), and clipboard manipulation. While clipboard operations are typically Write-category, the primary action is executing an OCR pipeline on captured screen content, which qualifies as Execute.

From the tool's definition Tool description states 'Capture active window, run AI OCR (qwen-vl via iflow), copy result to clipboard.' The terms 'capture active window' and 'run AI OCR' indicate execution of external operations (screen capture and AI inference).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cond_ocr Rate-limited

cond_ocr 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": {
    "cond_ocr": {
      "limits": [
        {
          "counter": "cond_ocr_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 TermPipe MCP, so you can run agents against it safely.

FAQ

Questions about cond_ocr

What does the cond_ocr tool do? +

Capture active window, run AI OCR (qwen-vl via iflow), copy result to clipboard. It is categorised as a Execute tool in the TermPipe MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cond_ocr? +

Register the TermPipe MCP server in PolicyLayer and add a rule for cond_ocr: 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_ocr? +

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

Can I rate-limit cond_ocr? +

Yes. Add a rate_limit block to the cond_ocr 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_ocr completely? +

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

cond_ocr 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.