Run AI OCR on an existing image file and copy result to clipboard.
AI agents invoke cond_ocr_file 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.
This tool executes an OCR operation on a file, which is a computational process triggered by the tool invocation. While not as severe as arbitrary shell command execution, it still qualifies as Execute because it runs code/algorithms with effects dependent on user-supplied arguments (the image file).
From the tool's definition Tool performs OCR processing on image files and copies results to clipboard. 'Run AI OCR' indicates execution of an external operation (OCR algorithm) whose output depends on the image argument provided.
Attacks that exploit this kind of access
Run AI OCR on an existing image file and 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.
Register the TermPipe MCP server in PolicyLayer and add a rule for cond_ocr_file: 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.
cond_ocr_file is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the cond_ocr_file 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.
Set action: deny in the PolicyLayer policy for cond_ocr_file. 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.
cond_ocr_file 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →