Search for PagerDuty incidents by title/description.
AI agents call find_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 searches and retrieves incident information from PagerDuty, which is a read-only operation with no side effects. It does not create, modify, delete, or execute any operations—it only queries existing data. The low severity reflects minimal risk; misuse would only expose incident information that an authorized user might already access.
From the tool's definition The tool 'Search for PagerDuty incidents by title/description' performs a query operation that retrieves incident data without modifying or deleting any information.
Attacks that exploit this kind of access
Search for PagerDuty incidents by title/description. 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 find_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.
find_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 find_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 find_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.
find_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 →