Scan text, web pages and MCP tool descriptions for prompt injection and tool poisoning before your agent trusts them. Free preview and MCP tool scan_text; full scans via x402 at $0.003 USDC on Base.
Scored across 3 tools
Each tool targets a clearly distinct input type: raw text (scan_text), a web page URL (scan_url), and MCP/function-calling definitions (scan_tools). Descriptions explicitly cross-reference each other ('Use scan_url when you only have a link', 'Use scan_text for ordinary content'), leaving no meaningful overlap or room for misselection.
All three tools follow the identical scan_<input_type> pattern (scan_text, scan_url, scan_tools). This is a tight, predictable convention that makes the tool surface trivially learnable.
Three tools is on the thin side, but each covers a genuinely different input channel (text, URL, tool definitions) and none is redundant. The scoping is deliberate rather than incomplete, though a slightly richer surface (e.g. batch or file scans) would justify more tools.
The surface covers the main injection vectors an agent encounters: inline content, browsed pages, and installed tool schemas, with consistent return shapes. Minor gaps remain—no direct file/binary/PDF ingestion or batch orchestration endpoint—but these are workable since callers can extract text and use scan_text or scan_tools.
Scans untrusted text for prompt injection before your agent reads or acts on it: web page text, emails, documents, tool results or another agent's message. Flags instruction overrides, jailbreak personas, system-prompt extraction, fake delimiters, exfiltration URLs, tool hijacking, hidden Unicode and encoded payloads (deterministic rules). Use scan_url when you only have a link (it also checks hidden HTML) and scan_tools for MCP tool definitions. Text up to 100000 characters. Free: 30 calls/day per IP shared by scan_text, scan_url and scan_tools, with full results (max 10/min; invalid input is not counted). After that the tool returns an error with the x402 pay URL ($0.003 USDC on Base, Polygon, Arbitrum One or Solana per call at https://api.youraitools.co/injectscan/v1/scan) or prepaid credits. Returns risk_score (0-100), verdict (safe | suspicious | malicious), flagged, categories[] {category, score, description}, findings[] {rule, category, start, end, text} and free_tier usage. Read-only safety signal, not a guarantee.
Inputs: text (required).
Checks MCP / function-calling tool definitions for tool poisoning (hidden instructions, data-exfiltration requests, hijack attempts in names, descriptions and schemas) before your agent installs or calls them. Use scan_text for ordinary content and scan_url for web pages. Up to 100 tools per call. Free: 30 calls/day per IP shared by scan_text, scan_url and scan_tools, with full results (max 10/min; invalid input is not counted). After that the tool returns an error with the x402 pay URL ($0.003 USDC on Base, Polygon, Arbitrum One or Solana per call at https://api.youraitools.co/injectscan/v1/scan) or prepaid credits. Returns the worst risk_score/verdict, flagged, tools_scanned, tools_flagged and tools[] {index, name, risk_score, verdict, categories, findings[] {field, rule, text}}. Read-only safety signal, not a guarantee.
Inputs: tools (required).
Fetches a public web page and scans its visible text plus hidden HTML (comments, hidden elements, alt/aria/meta text) for prompt injection, before your agent browses or summarizes it. Use scan_text if you already have the content and scan_tools for MCP tool definitions. Respects robots.txt and refuses private/internal hosts. Free: 30 calls/day per IP shared by scan_text, scan_url and scan_tools, with full results (max 10/min; invalid input is not counted). After that the tool returns an error with the x402 pay URL ($0.003 USDC on Base, Polygon, Arbitrum One or Solana per call at https://api.youraitools.co/injectscan/v1/scan) or prepaid credits. Returns risk_score (0-100), verdict (safe | suspicious | malicious), flagged, categories[] {category, score, description}, findings[] with location (visible or hidden), url, finalUrl, title, hidden_html {segments_checked, flagged} and page {status, contentType}. Read-only safety signal, not a guarantee.
Inputs: url (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.