Accept an approval.
AI agents use accept_incident_approval to create or update resources in InvGate Service Desk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your InvGate Service Desk environment.
Accepting an approval changes its state in the system, which is a reversible write operation (the approval could potentially be cancelled or revised). It does not delete data, execute code, or involve financial transactions. The blast radius is medium because approving an incident could trigger downstream workflow actions.
From the tool's definition Accept an approval — this modifies the state of an approval record within an incident workflow.
Attacks that exploit this kind of access
Accept an approval. It is categorised as a Write tool in the InvGate Service Desk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the InvGate Service Desk MCP server in PolicyLayer and add a rule for accept_incident_approval: 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 InvGate Service Desk. Nothing to install.
accept_incident_approval 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 accept_incident_approval 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 accept_incident_approval. 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.
accept_incident_approval is provided by the InvGate Service Desk MCP server (oci:ghcr.io/tracegazer/invgate-service-desk-mcp:0.2.0). 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 →