AI agents call list_contact_points to retrieve information from Grafana FastMCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or enumerate contact points (notification endpoints) from Grafana alerts—a read operation with no side effects. While the description is absent, the 'list_' prefix and sibling tools (create_incident, add_activity_to_incident) that modify data suggest this queries existing data.
From the tool's definition Tool name 'list_contact_points' and context of Grafana alert management suggest data retrieval of contact point configurations. Empty description limits confidence, but naming pattern aligns with read operations (list_* typically queries without modification).
Documented attack patterns abuse exactly the kind of access list_contact_points gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Grafana FastMCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list_contact_points:
{
"version": "1",
"default": "deny",
"tools": {
"list_contact_points": {}
}
}list_contact_points is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
list_contact_points. It is categorised as a Read tool in the Grafana FastMCP Server MCP Server, which means it retrieves data without modifying state.
Register the Grafana FastMCP Server MCP server in PolicyLayer and add a rule for list_contact_points: 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 FastMCP Server. Nothing to install.
list_contact_points 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_contact_points 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_contact_points. 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_contact_points is provided by the Grafana FastMCP Server MCP server (sandersouza/grafanafastmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Grafana FastMCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
45 Grafana FastMCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.