AI agents call enhance_prompt to retrieve information from Mirdan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to read and retrieve quality standards, architectural patterns, and codebase context to enhance prompts. No indication of data modification, code execution, or destructive operations. Sibling tools are all read-only analysis and validation functions. Confidence is moderate (0.7) due to empty description, but the name and context strongly suggest a read-only enhancement operation.
From the tool's definition Tool name 'enhance_prompt' and server description indicate this tool augments developer prompts with context and standards from the codebase, similar to sibling read-only tools like 'get_quality_standards', 'scan_conventions', and 'scan_dependencies'.
Attacks that exploit this kind of access
enhance_prompt. It is categorised as a Read tool in the Mirdan MCP Server, which means it retrieves data without modifying state.
Register the Mirdan MCP server in PolicyLayer and add a rule for enhance_prompt: 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 Mirdan. Nothing to install.
enhance_prompt 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 enhance_prompt 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 enhance_prompt. 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.
enhance_prompt is provided by the Mirdan MCP server (s-corkum/mirdan). 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 →