Get current PagerDuty incidents.
AI agents call get_current_incidents to retrieve information from Incident Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves incident information from PagerDuty without modifying, executing operations on, or deleting any data. It is a straightforward read operation with minimal blast radius—misuse would only expose existing incident data, not cause system changes or data loss.
From the tool's definition Tool name 'get_current_incidents' and description 'Get current PagerDuty incidents' indicate data retrieval with no modification. The verb 'Get' and lack of any mutation language (create, update, delete, modify) confirm this is a query operation.
Attacks that exploit this kind of access
Get current PagerDuty incidents. It is categorised as a Read tool in the Incident Agent MCP Server, which means it retrieves data without modifying state.
Register the Incident Agent MCP server in PolicyLayer and add a rule for get_current_incidents: 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 Incident Agent. Nothing to install.
get_current_incidents 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 get_current_incidents 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 get_current_incidents. 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.
get_current_incidents is provided by the Incident Agent MCP server (jayliumlp/incident-agent). 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 →