IDCheck: poll the status of a verification process previously created via the Unico Web/Mobile SDK or API. Returns { status (CREATED | IN_PROGRESS | FINISHED | EXPIRED | CANCELED), verdict, finished_at, score, reasons[] }. Use this to drive your KYC state machine after the user finishes the SDK c...
AI agents call get_process_status to retrieve information from Mcp Ap2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the current state of a KYC verification process that was previously initiated. It is a pure read operation that queries state without side effects. The context shows this is part of a financial identity verification system (IDCheck), but the tool itself only observes and reports status—it does not move money, execute commands, modify records, or trigger irreversible actions.
From the tool's definition Tool performs polling/status check operation: 'poll the status of a verification process'. Returns read-only status information (status, verdict, finished_at, score, reasons) with no data modification, deletion, or external operation triggering.
Documented attack patterns abuse exactly the kind of access get_process_status gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for get_process_status:
{
"version": "1",
"default": "deny",
"tools": {
"get_process_status": {}
}
}get_process_status is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
IDCheck: poll the status of a verification process previously created via the Unico Web/Mobile SDK or API. Returns { status (CREATED | IN_PROGRESS | FINISHED | EXPIRED | CANCELED), verdict, finished_at, score, reasons[] }. Use this to drive your KYC state machine after the user finishes the SDK capture flow. It is categorised as a Read tool in the Mcp Ap2 MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for get_process_status: 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 Ap2. Nothing to install.
get_process_status 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 get_process_status 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 get_process_status. 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.
get_process_status is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.