Scan a single MCP server definition for security vulnerabilities without requiring a full configuration file.
AI agents call scan_server to retrieve information from Agent Audit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a security scan/analysis operation — it reads and inspects an MCP server definition to detect vulnerabilities. This is fundamentally a read/query operation with no persistent side effects.
From the tool's definition Scan a single MCP server definition for security vulnerabilities without requiring a full configuration file
Attacks that exploit this kind of access
Scan a single MCP server definition for security vulnerabilities without requiring a full configuration file. It is categorised as a Read tool in the Agent Audit MCP Server, which means it retrieves data without modifying state.
Register the Agent Audit MCP server in PolicyLayer and add a rule for scan_server: 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 Agent Audit. Nothing to install.
scan_server 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_server 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_server. 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_server is provided by the Agent Audit MCP server (piiiico/agent-audit). 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 →