AI agents call scan_dependencies 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.
This tool performs a non-destructive, informational scan that retrieves known vulnerability data. It does not execute code on the system, does not modify dependencies, does not delete data, and does not move money. The 'scan' verb combined with 'for known vulnerabilities' indicates passive discovery and reporting rather than remediation or execution.
From the tool's definition Tool name 'scan_dependencies' and description 'Scan project dependencies for known vulnerabilities' indicate a read-only operation that queries and retrieves vulnerability information about dependencies without modifying data or executing arbitrary code.
Attacks that exploit this kind of access
Scan project dependencies for known vulnerabilities. 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 scan_dependencies: 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.
scan_dependencies 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 scan_dependencies 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 scan_dependencies. 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.
scan_dependencies 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 →