AI agents use add_activity_to_incident to create or update resources in Grafana FastMCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Grafana FastMCP Server environment.
The tool adds a user note to an incident, which is a create operation on incident data. This is reversible (notes can typically be edited or deleted), making it a Write rather than Execute or Destructive action. The blast radius is low because adding notes is non-critical metadata that does not affect alerting logic, data deletion, or financial operations.
From the tool's definition Tool name and description: 'Add a user note to an incident' — this creates/adds new data (a note) to an existing incident record, which is a reversible write operation.
Documented attack patterns abuse exactly the kind of access add_activity_to_incident 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 add_activity_to_incident:
{
"version": "1",
"default": "deny",
"tools": {
"add_activity_to_incident": {
"limits": [
{
"counter": "add_activity_to_incident_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_activity_to_incident stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Add a user note to an incident. It is categorised as a Write tool in the Grafana FastMCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Grafana FastMCP Server MCP server in PolicyLayer and add a rule for add_activity_to_incident: 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.
add_activity_to_incident is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_activity_to_incident 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 add_activity_to_incident. 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.
add_activity_to_incident 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.