Return detected entrypoints and trust metadata.
AI agents call attack_surface to retrieve information from Trailmark MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and returns information about detected entrypoints and trust metadata from a code repository. This is a read/query operation with no side effects. However, the data returned (attack surface information) could be sensitive from a security perspective, slightly elevating severity, but the action itself is purely read-based.
From the tool's definition Return detected entrypoints and trust metadata
Attacks that exploit this kind of access
Return detected entrypoints and trust metadata. It is categorised as a Read tool in the Trailmark MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Trailmark MCP Server MCP server in PolicyLayer and add a rule for attack_surface: 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 Trailmark MCP Server. Nothing to install.
attack_surface 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 attack_surface 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 attack_surface. 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.
attack_surface is provided by the Trailmark MCP Server MCP server (parsiya/trailmark-mcp-server). 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 →