OCR a Brazilian ID document (RG / CNH / CRLV / proof of residence / passport). Returns extracted structured fields per document type. POST /v1/documents/ocr.
AI agents call documents_ocr 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 reads and parses document images to extract text and structured data. It has no side effects, creates no resources, executes no code, and modifies no persistent state. The confidence is high because the function is clearly read-only data extraction despite the POST verb being used for the API call itself.
From the tool's definition Tool description states 'OCR a Brazilian ID document... Returns extracted structured fields per document type'. OCR (Optical Character Recognition) retrieves and extracts data from images; it performs no modification, deletion, or execution.
Documented attack patterns abuse exactly the kind of access documents_ocr 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 documents_ocr:
{
"version": "1",
"default": "deny",
"tools": {
"documents_ocr": {}
}
} documents_ocr 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.
OCR a Brazilian ID document (RG / CNH / CRLV / proof of residence / passport). Returns extracted structured fields per document type. POST /v1/documents/ocr. 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 documents_ocr: 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.
documents_ocr 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 documents_ocr 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 documents_ocr. 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.
documents_ocr 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.