AI agents call get_log_cache to retrieve information from Grafana without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs inspection and introspection of internal cache state without side effects. It retrieves information about cached log datasources, labels, and service resolution status. There is no capability to modify, delete, execute, or move resources, placing it squarely in the Read category with low severity since misuse would only expose cached metadata.
From the tool's definition Tool description states 'Inspect the local log cache' and 'Use to confirm what is cached' — actions limited to retrieving and viewing cached data with no modification, deletion, or execution capabilities. Server description emphasizes 'read-only access'.
Attacks that exploit this kind of access
Inspect the local log cache (log datasources, detected labels, resolved services). Use to confirm what is cached and whether a service has been resolved before. It is categorised as a Read tool in the Grafana MCP Server, which means it retrieves data without modifying state.
Register the Grafana MCP server in PolicyLayer and add a rule for get_log_cache: 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 Grafana. Nothing to install.
get_log_cache 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_log_cache 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_log_cache. 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_log_cache is provided by the Grafana MCP server (ninanung/grafana-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 →