Gửi notification cho request
AI agents use send_request_notification to create or update resources in ServiceDesk Plus MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ServiceDesk Plus MCP Server environment.
This tool sends a notification related to a request, which is a Write action (triggering an outbound communication/message). It does not delete data or execute arbitrary code. Misuse could result in spam or misleading notifications sent to users, hence medium severity.
From the tool's definition 'send_request_notification' and description 'Gửi notification cho request' (Send notification for request)
Attacks that exploit this kind of access
Gửi notification cho request. It is categorised as a Write tool in the ServiceDesk Plus MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ServiceDesk Plus MCP Server MCP server in PolicyLayer and add a rule for send_request_notification: 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 ServiceDesk Plus MCP Server. Nothing to install.
send_request_notification 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 send_request_notification 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 send_request_notification. 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.
send_request_notification is provided by the ServiceDesk Plus MCP Server MCP server (thichcode/servicedeskplus_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 →