AI agents call list_trails to retrieve information from Clawmarks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about trails stored in the knowledge graph. It is purely a read operation that queries the local JSON file for trail metadata. No data is created, modified, deleted, or executed. The filtering capability is a standard read operation parameter.
From the tool's definition Tool name 'list_trails' and description 'List all trails, optionally filtered by status' indicate retrieval/querying of existing trail data with no modification or side effects.
Attacks that exploit this kind of access
List all trails, optionally filtered by status. It is categorised as a Read tool in the Clawmarks MCP Server, which means it retrieves data without modifying state.
Register the Clawmarks MCP server in PolicyLayer and add a rule for list_trails: 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 Clawmarks. Nothing to install.
list_trails 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 list_trails 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 list_trails. 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.
list_trails is provided by the Clawmarks MCP server (mrilikecoding/clawmarks). 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 →