AI agents call validate_code_quality 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 validate or check code quality metrics against standards, which is a read operation that inspects data without side effects. No evidence suggests it modifies, executes arbitrary code, deletes resources, or commits financial transactions. The sibling tools on this server are all analysis/orchestration oriented rather than destructive.
From the tool's definition Tool name 'validate_code_quality' combined with server context listing 'validate_quick' and 'verify_plan' as sibling analysis/validation tools suggests inspection or assessment without modification.
Attacks that exploit this kind of access
validate_code_quality. 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 validate_code_quality: 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.
validate_code_quality 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 validate_code_quality 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 validate_code_quality. 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.
validate_code_quality 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 →