AI agents call list_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 tool retrieves information about Grafana datasources without modifying, executing, or deleting anything. It has minimal blast radius—exposing datasource names and types provides reconnaissance value but no operational impact. The read-only design and retrieval nature clearly place it in the Read category.
From the tool's definition Tool is described as listing configured data sources with no modification capability. Server description explicitly states 'read-only access'. Action verb 'list' is a typical Read operation that retrieves configuration metadata without side effects.
Attacks that exploit this kind of access
List configured Grafana data sources. 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_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_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_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_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_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 →