インシデントの一覧を取得します。各種フィルター条件を指定できます。
AI agents call waroom_get_incidents to retrieve information from Waroom MCP 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 with optional filtering parameters. It performs a query operation that returns data without creating, modifying, deleting, or executing external operations. The read-only nature and lack of any state-changing operations places it firmly in the Read category with low severity, as misuse would only expose existing incident data rather than cause operational damage.
From the tool's definition Tool name contains 'get' and description translates to 'Retrieves a list of incidents. Various filter conditions can be specified.' The verb 'get' combined with 'list' operations indicates data retrieval without modification or side effects.
Attacks that exploit this kind of access
インシデントの一覧を取得します。各種フィルター条件を指定できます。. It is categorised as a Read tool in the Waroom MCP MCP Server, which means it retrieves data without modifying state.
Register the Waroom MCP server in PolicyLayer and add a rule for waroom_get_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 Waroom MCP. Nothing to install.
waroom_get_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 waroom_get_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 waroom_get_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.
waroom_get_incidents is provided by the Waroom MCP server (topotal/waroom-mcp). 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 →