Inspect a document (PDF or image) for authenticity signals: tampering / AI-generation indicators, arithmetic reconciliation (financial docs), and provenance. Provide the document inline, base64-encoded, as bytes_b64 (plus an optional filename so the engine routes PDF vs image correctly). This hos...
Risk signalsAccepts file system path (filename)
Part of the OpenWarrant server.
Free to start. No card required.
AI agents call verify_document to retrieve information from OpenWarrant without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though verify_document only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"verify_document": {}
}
}See the full OpenWarrant policy for all 4 tools.
These attack patterns abuse exactly the kind of access verify_document gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Inspect a document (PDF or image) for authenticity signals: tampering / AI-generation indicators, arithmetic reconciliation (financial docs), and provenance. Provide the document inline, base64-encoded, as bytes_b64 (plus an optional filename so the engine routes PDF vs image correctly). This hosted server runs remotely, so it can NOT read a local path; to verify a local file or a URL without base64-encoding, use the local stdio server (see the agent guide at /agents.md). Returns the headline result — risk_band (low/medium/high/insufficient/error), inspection_quality (coverage, orthogonal to risk), recommended_action, a summary, and the RISK-axis risk_findings. This is a SIGNAL, not a fraud verdict — a human or agent adjudicates. Use get_warrant(warrant_id) for the full evidence bundle. Identical bytes are cached by content hash — call check_document first to skip a redundant, paid inspection.. It is categorised as a Read tool in the OpenWarrant MCP Server, which means it retrieves data without modifying state.
Register the OpenWarrant MCP server in PolicyLayer and add a rule for verify_document: 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 OpenWarrant. Nothing to install.
verify_document 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 verify_document 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 verify_document. 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.
verify_document is provided by the OpenWarrant MCP server (https://www.stipple.sh/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 OpenWarrant tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.