AI agents call poll_until_complete to retrieve information from Ppdm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads/queries the status of an existing activity repeatedly until it completes. It does not create, modify, delete, or trigger any operations itself — it purely observes and returns state. The mention of 'use after trigger_backup' confirms it is a monitoring/waiting helper, not an action tool.
From the tool's definition Poll a PPDM activity until it reaches a terminal state... Returns the final activity record.
Attacks that exploit this kind of access
Poll a PPDM activity until it reaches a terminal state (SUCCEEDED, FAILED, CANCELED). Returns the final activity record. Use after trigger_backup to await completion. It is categorised as a Read tool in the Ppdm MCP Server, which means it retrieves data without modifying state.
Register the Ppdm MCP server in PolicyLayer and add a rule for poll_until_complete: 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 Ppdm. Nothing to install.
poll_until_complete 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 poll_until_complete 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 poll_until_complete. 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.
poll_until_complete is provided by the Ppdm MCP server (moodswing9/ppdm-mcp-server). 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 →