Query the internal CrewAI documentation RAG engine.
AI agents call crewai_query_knowledge to retrieve information from CrewAI MCP Orchestrator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a documentation system (RAG engine) to retrieve information. It is a read-only operation that retrieves data without side effects, altering data, executing code, or committing any irreversible actions. The lowest severity is appropriate since documentation queries pose minimal risk even if misused by an agent.
From the tool's definition Tool name 'crewai_query_knowledge' and description 'Query the internal CrewAI documentation RAG engine' indicate retrieval of information with no modification or execution of external operations.
Attacks that exploit this kind of access
Query the internal CrewAI documentation RAG engine. It is categorised as a Read tool in the CrewAI MCP Orchestrator MCP Server, which means it retrieves data without modifying state.
Register the CrewAI MCP Orchestrator MCP server in PolicyLayer and add a rule for crewai_query_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 CrewAI MCP Orchestrator. Nothing to install.
crewai_query_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 crewai_query_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 crewai_query_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.
crewai_query_knowledge is provided by the CrewAI MCP Orchestrator MCP server (ssolis-ti/crewai-mcp-hq). 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 →