AI agents call get_trail 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 returns existing trail data from the knowledge graph without modifying, deleting, or executing any operations. It is purely informational—fetching clawmarks and their organization for inspection. No data is created, modified, deleted, or executed as a result of calling this tool.
From the tool's definition Tool name 'get_trail' and description 'Get a trail with all its clawmarks' indicate a retrieval operation. The verb 'Get' and the overall context of retrieving stored annotation data for review represent a read-only query with no side effects.
Attacks that exploit this kind of access
Get a trail with all its clawmarks. 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 get_trail: 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.
get_trail 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 get_trail 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 get_trail. 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.
get_trail 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 →