AI agents call list_log_datasources 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 is a purely informational retrieval operation that enumerates available log data sources without querying, modifying, or executing any operations. The caching mechanism further confirms this is a passive read operation. Low severity because listing datasources reveals metadata about log sources but does not expose sensitive log contents or permit direct log access—only inventory of available sources.
From the tool's definition Tool lists Grafana datasources (descriptive operation). Server description explicitly states 'read-only access to log data'. No modification, deletion, or execution capability.
Attacks that exploit this kind of access
List Grafana datasources that store logs (Loki, Elasticsearch, CloudWatch, OpenSearch, Splunk). Cached. 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 list_log_datasources: 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.
list_log_datasources 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 list_log_datasources 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 list_log_datasources. 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.
list_log_datasources 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 →