Get current memory engine statistics. Args: namespace: Filter stats to a specific namespace. None for global stats. Returns counts of active, consolidated, tombstoned, and archived memories, entity and edge counts, open conflicts, pending triggers, active patterns, and internal index sizes.
AI agents call memory_stats to retrieve information from Yantrikdb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports statistics about the memory engine's internal state. It performs no data modification, deletion, or execution of external operations. The optional namespace parameter is a read filter, not a write operation. The tool's sole purpose is introspection and monitoring, making it a pure Read operation with low risk.
From the tool's definition Tool name is 'memory_stats' and description states it 'Get[s] current memory engine statistics' returning 'counts of active, consolidated, tombstoned, and archived memories, entity and edge counts, open conflicts, pending triggers, active patterns, and…
Documented attack patterns abuse exactly the kind of access memory_stats gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Yantrikdb, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_stats:
{
"version": "1",
"default": "deny",
"tools": {
"memory_stats": {}
}
}memory_stats is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get current memory engine statistics. Args: namespace: Filter stats to a specific namespace. None for global stats. Returns counts of active, consolidated, tombstoned, and archived memories, entity and edge counts, open conflicts, pending triggers, active patterns, and internal index sizes. It is categorised as a Read tool in the Yantrikdb MCP Server, which means it retrieves data without modifying state.
Register the Yantrikdb 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 Yantrikdb. 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 Yantrikdb MCP server (yantrikos/yantrikdb-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 Yantrikdb tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 Yantrikdb tools catalogued and risk-classified — across an index of 42,500+ MCP servers.