Get cache statistics for indexed directories
AI agents call cache_stats to retrieve information from Code Search MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and returns cache statistics. It has no side effects, cannot modify data, execute code, delete information, or move money. The action is purely informational retrieval, fitting the 'Read' category. Severity is low because exposure of cache statistics poses minimal risk to an AI agent's ability to cause harm.
From the tool's definition Tool is called 'cache_stats' and described as 'Get cache statistics for indexed directories' - it retrieves statistical information about cache state without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Get cache statistics for indexed directories. It is categorised as a Read tool in the Code Search MCP MCP Server, which means it retrieves data without modifying state.
Register the Code Search MCP server in PolicyLayer and add a rule for 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 Code Search MCP. Nothing to install.
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 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 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.
cache_stats is provided by the Code Search MCP server (llmtooling/code-search-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 →