Document validation — OCR + authenticity check on RG / CNH / passport / proof of residence. Returns structured fields + authenticity_score. POST /v1/checks/document.
AI agents call document_check 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.
Document validation via OCR is fundamentally a read operation that extracts and analyzes data from documents. While authenticity scoring involves computation, the tool does not create, modify, delete, or execute arbitrary operations. It has minimal blast radius—misuse would retrieve or validate document metadata without causing irreversible harm, financial exposure, or system compromise.
From the tool's definition Tool performs 'OCR + authenticity check' and 'Returns structured fields + authenticity_score.' It validates and reads documents without modifying, deleting, or executing commands. No financial transactions, destructive operations, or code execution involved.
Documented attack patterns abuse exactly the kind of access document_check 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 document_check:
{
"version": "1",
"default": "deny",
"tools": {
"document_check": {}
}
}document_check 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.
Document validation — OCR + authenticity check on RG / CNH / passport / proof of residence. Returns structured fields + authenticity_score. POST /v1/checks/document. 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 document_check: 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.
document_check 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 document_check 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 document_check. 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.
document_check 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.