Query the entity knowledge graph extracted from memories. Find people, concepts, tools, and their relationships.
AI agents call memory_entity_query to retrieve information from MCP Router without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs data retrieval without modification—it queries and finds information from a knowledge graph. This is a Read operation. The severity is medium rather than low because the knowledge graph may contain sensitive relationship data about people, concepts, and tools that could reveal operational patterns, organizational structures, or system dependencies if queried maliciously by an AI agent.
From the tool's definition Tool description states 'Query the entity knowledge graph extracted from memories. Find people, concepts, tools, and their relationships.' This is fundamentally a retrieval operation that queries data to extract information.
Attacks that exploit this kind of access
Query the entity knowledge graph extracted from memories. Find people, concepts, tools, and their relationships. It is categorised as a Read tool in the MCP Router MCP Server, which means it retrieves data without modifying state.
Register the MCP Router MCP server in PolicyLayer and add a rule for memory_entity_query: 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 MCP Router. Nothing to install.
memory_entity_query 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 memory_entity_query 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 memory_entity_query. 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.
memory_entity_query is provided by the MCP Router MCP server (justinpreston/mcp-router). 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 →