AI agents call mem0_graph_query to retrieve information from VibeServe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a query operation on a knowledge graph to retrieve entity relationships. This is a read-only operation that retrieves or queries data without modifying, deleting, or executing external actions. The use of 'Query' in both name and description, combined with the passive retrieval of 'entity relationships', confirms this as a Read category tool with low severity.
From the tool's definition Tool name 'mem0_graph_query' and description 'Query the mem0 knowledge graph for entity relationships' indicate data retrieval with no side effects.
Attacks that exploit this kind of access
Query the mem0 knowledge graph for entity relationships. It is categorised as a Read tool in the VibeServe MCP Server, which means it retrieves data without modifying state.
Register the VibeServe MCP server in PolicyLayer and add a rule for mem0_graph_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 VibeServe. Nothing to install.
mem0_graph_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 mem0_graph_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 mem0_graph_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.
mem0_graph_query is provided by the VibeServe MCP server (ncsound919/vibeserve). 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 →