AI agents call compare_engines to retrieve information from Ocr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to compare OCR engine performance by retrieving and analyzing data about different engines' accuracy or capabilities. It performs no modifications, deletions, or external operations—only data retrieval and comparison. The lack of a specific description lowers confidence slightly, but the contextual evidence from the server's purpose and sibling tools strongly suggests a Read operation.
From the tool's definition Tool name 'compare_engines' combined with sibling tools 'evaluate_accuracy' and 'list_engines' indicate data retrieval and analysis operations. The server description emphasizes 'accuracy handling and evaluation' and 'score and compare' engines.
Attacks that exploit this kind of access
compare_engines. It is categorised as a Read tool in the Ocr MCP Server, which means it retrieves data without modifying state.
Register the Ocr MCP server in PolicyLayer and add a rule for compare_engines: 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 Ocr. Nothing to install.
compare_engines is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the compare_engines 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 compare_engines. 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.
compare_engines is provided by the Ocr MCP server (prekzursil/abbyy-finereader-ocr-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 →