list_annotations
AI agents call list_annotations to retrieve information from Mcp Read Only Grafana without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries annotations from Grafana without side effects. The 'list' verb is characteristic of Read operations. While the description is empty, the tool name is unambiguous and consistent with the server's stated read-only default behavior. The presence of separate destructive/write tools (delete_*, create_*) on the same server further confirms this is a read-only operation.
From the tool's definition Tool name 'list_annotations' with 'list' prefix indicates data retrieval without mutation. Server description emphasizes 'read-only access by default.' No delete, create, update, or execute operations implied by the name.
Attacks that exploit this kind of access
list_annotations. It is categorised as a Read tool in the Mcp Read Only Grafana MCP Server, which means it retrieves data without modifying state.
Register the Mcp Read Only Grafana MCP server in PolicyLayer and add a rule for list_annotations: 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 Mcp Read Only Grafana. Nothing to install.
list_annotations 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_annotations 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_annotations. 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_annotations is provided by the Mcp Read Only Grafana MCP server (lukleh/mcp-read-only-grafana). 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 →