Counts: total memories, total decisions, total journal entries, top tags.
AI agents call memory_stats to retrieve information from Nexus Core without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves aggregated statistics about stored data (memory counts, decision counts, journal entry counts, tag frequencies). It performs no write, delete, execute, or financial operations. The use of 'Counts' and 'top tags' clearly indicates read-only queries against existing data structures. There is no ability to modify, destroy, or trigger external actions.
From the tool's definition Tool description explicitly states it 'Counts: total memories, total decisions, total journal entries, top tags' — pure data retrieval operations with no modification, deletion, or side effects.
Attacks that exploit this kind of access
Counts: total memories, total decisions, total journal entries, top tags. It is categorised as a Read tool in the Nexus Core MCP Server, which means it retrieves data without modifying state.
Register the Nexus Core MCP server in PolicyLayer and add a rule for memory_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 Nexus Core. Nothing to install.
memory_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 memory_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 memory_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.
memory_stats is provided by the Nexus Core MCP server (noumenon-ai/nexus-core). 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 →