Get embedding cache statistics
AI agents call get_cache_stats to retrieve information from Self-Improving Memory MCP 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 an embedding cache. It performs a query/inspection operation that only reads data without creating, modifying, deleting, or executing any operations. The scope is limited to cache metadata and statistics, presenting no destructive or financial risk.
From the tool's definition Tool name is 'get_cache_stats' and description states 'Get embedding cache statistics' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get embedding cache statistics. It is categorised as a Read tool in the Self-Improving Memory MCP MCP Server, which means it retrieves data without modifying state.
Register the Self-Improving Memory MCP server in PolicyLayer and add a rule for get_cache_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 Self-Improving Memory MCP. Nothing to install.
get_cache_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 get_cache_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 get_cache_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.
get_cache_stats is provided by the Self-Improving Memory MCP server (superpitt/self-improving-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 →