IDCheck: fetch the structured OCR result for a finished process — typed fields (name, document number, issuer, birthdate, etc.) plus per-field confidence and the raw text blocks. Returns 409 if the process has not yet reached FINISHED.
AI agents call get_extracted_data 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 personal identification data (name, document number, issuer, birthdate, confidence scores, raw text blocks) extracted via OCR from identity documents.
From the tool's definition Tool description states it 'fetch[es] the structured OCR result' and 'Returns 409 if the process has not yet reached FINISHED' — a read-only retrieval operation with no modifications.
Documented attack patterns abuse exactly the kind of access get_extracted_data 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_extracted_data:
{
"version": "1",
"default": "deny",
"tools": {
"get_extracted_data": {}
}
}get_extracted_data 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: fetch the structured OCR result for a finished process — typed fields (name, document number, issuer, birthdate, etc.) plus per-field confidence and the raw text blocks. Returns 409 if the process has not yet reached FINISHED. 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_extracted_data: 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_extracted_data 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_extracted_data 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_extracted_data. 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_extracted_data 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.