update_contact_point
AI agents use update_contact_point to create or update resources in Mcp Read Only Grafana — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Read Only Grafana environment.
This tool modifies notification contact points in Grafana (email, Slack, PagerDuty endpoints, etc.). While reversible via subsequent updates, misconfiguration could disrupt critical alerting infrastructure, affecting incident response. Classified as Write (not Destructive, as updates are reversible) with high severity due to potential operational impact on monitoring systems.
From the tool's definition Tool name 'update_contact_point' indicates modification of contact point configuration. Server description explicitly states it provides 'write-capable command for mutations.' Sibling tools include create/delete operations on contact points, confirming this…
Attacks that exploit this kind of access
update_contact_point. It is categorised as a Write tool in the Mcp Read Only Grafana MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Read Only Grafana MCP server in PolicyLayer and add a rule for update_contact_point: 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.
update_contact_point 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 update_contact_point 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 update_contact_point. 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.
update_contact_point 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 →