AI agents call graph_stats to retrieve information from Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and returns statistics about an existing knowledge graph structure without creating, modifying, deleting, or executing operations. This is a read-only retrieval action with no side effects or risk of data loss or unintended operations. The low severity reflects minimal blast radius if misused—at worst, an agent could repeatedly query statistics without causing harm.
From the tool's definition Tool name is 'graph_stats' and description states 'Get statistics about the knowledge graph' - both indicate a retrieval operation with no modification capability.
Attacks that exploit this kind of access
Get statistics about the knowledge graph. It is categorised as a Read tool in the Memory MCP Server, which means it retrieves data without modifying state.
Register the Memory MCP server in PolicyLayer and add a rule for graph_stats: 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 Memory. Nothing to install.
graph_stats 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 graph_stats 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 graph_stats. 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.
graph_stats is provided by the Memory MCP server (shaktisinhchavda/memory-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 →