AI agents call search_knowledge to retrieve information from Maestro without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search operation against a knowledge base, which is a read-only action that retrieves information without side effects. No data creation, modification, deletion, or execution of external operations is implied. The low severity reflects minimal blast radius—an AI agent cannot cause harm by searching a knowledge base.
From the tool's definition Tool name 'search_knowledge' combined with description 'Busca na base de conhecimento' (Search in the knowledge base) indicates a query/retrieval operation with no modification capability.
Attacks that exploit this kind of access
Busca na base de conhecimento. It is categorised as a Read tool in the Maestro MCP Server, which means it retrieves data without modifying state.
Register the Maestro MCP server in PolicyLayer and add a rule for search_knowledge: 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 Maestro. Nothing to install.
search_knowledge 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_knowledge 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_knowledge. 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_knowledge is provided by the Maestro MCP server (matheus-gama-deluna/maestro). 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 →