add_issue
AI agents use add_issue to create or update resources in MCP IT Help Desk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP IT Help Desk environment.
The tool creates new data entries (issues) in a database system reversibly—issues can be modified or deleted later. This is a Write operation rather than Read (not just querying) or Destructive (data can be undone). Severity is medium because misuse could spam the system or create false issues that burden support staff, but financial or data loss consequences are unlikely.
From the tool's definition Tool named 'add_issue' on an IT Help Desk server that routes to experts via Django DB. The description is empty, but the name and server context indicate creation of new issue records in a database.
Attacks that exploit this kind of access
add_issue. It is categorised as a Write tool in the MCP IT Help Desk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP IT Help Desk MCP server in PolicyLayer and add a rule for add_issue: 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 MCP IT Help Desk. Nothing to install.
add_issue 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 add_issue 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 add_issue. 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.
add_issue is provided by the MCP IT Help Desk MCP server (minasenel/mcp-it-helpdesk). 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 →