AI agents call search_playbooks to retrieve information from Cawskills without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval/search tool that queries existing playbooks and returns results. No side effects, no modifications, no code execution. Matches the Read category definition: retrieves or queries data with no side effects (search, list, get, fetch).
From the tool's definition Tool description states it 'Search across workflow playbooks for a query string and return matching excerpts with context' — a pure query/search operation that retrieves information without modifying, deleting, or executing anything.
Attacks that exploit this kind of access
Search across workflow playbooks for a query string and return matching excerpts with context. It is categorised as a Read tool in the Cawskills MCP Server, which means it retrieves data without modifying state.
Register the Cawskills MCP server in PolicyLayer and add a rule for search_playbooks: 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 Cawskills. Nothing to install.
search_playbooks 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 search_playbooks 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 search_playbooks. 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.
search_playbooks is provided by the Cawskills MCP server (shanksg/clawskills). 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 →