AI agents call knowledge_search to retrieve information from Willow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from a knowledge base without side effects. It performs a read-only operation to search content. Even though it accesses a Postgres backend, the search functionality itself does not create, modify, delete, or execute operations. The presence of SAP/1.0 authorization on every call provides access control but does not change the tool's fundamental read-only nature.
From the tool's definition Tool name contains 'search' and description states 'Search the Postgres knowledge base' with no mention of modification, deletion, or execution capabilities. The verb 'search' indicates a query operation.
Attacks that exploit this kind of access
Search the Postgres knowledge base (LOAM) by content. It is categorised as a Read tool in the Willow MCP Server, which means it retrieves data without modifying state.
Register the Willow MCP server in PolicyLayer and add a rule for knowledge_search: 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 Willow. Nothing to install.
knowledge_search 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 knowledge_search 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 knowledge_search. 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.
knowledge_search is provided by the Willow MCP server (rudi193-cmd/willow-mcp). 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 →