AI agents call list_tags 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 only queries and returns information (a list of tags) from the local knowledge graph stored in the JSON file. It has no side effects, does not create, modify, or delete any clawmarks or trails, and does not execute external operations. It falls clearly into the Read category with low severity since exposing a list of tags poses minimal security risk even if misused by an agent.
From the tool's definition Tool name is 'list_tags' with description 'List all unique tags used across all clawmarks' — a pure read operation that retrieves and displays metadata without modifying any data.
Attacks that exploit this kind of access
List all unique tags used across all 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 list_tags: 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_tags 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_tags 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_tags. 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_tags 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 →