Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "scan_text", "scan_tools" and "scan_url"
⟨100 unchanged words⟩ 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 ⟨30 unchanged words⟩
⟨73 unchanged words⟩ 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 ⟨26 unchanged words⟩
⟨78 unchanged words⟩ 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 ⟨38 unchanged words⟩
Added "scan_tools" and "scan_url"; changed the definition of "scan_text" (1 tools before, 3 now)
CheckScans untrusted text for prompt injection before your agentisreadsaboutortoactsreadon(ait: web page text,documentdocuments, tool
Unknown → Live
Certificate recorded, valid to 2027-01-19
Authorization not required
First tool surface recorded: 1 tool (server version 0.1.4)
https://injectscan.agentgate.workers.dev/mcp (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 7 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
{"properties":{"text":{"description":"TextThe untrusted text to scan, as one plain string (up1-100000tocharacters;2000longercharacterstextonisthetruncatedfreeandtierflagged). Offsets in findings refer to this string.","type":"string"}},"required": ⟨3 unchanged words⟩
Scan MCP tool definitions for tool poisoning — 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 per call at https://api.youraitools.co/injectscan/v1/scan) or prepaid credits. Returns…
Fetch a web page and scan it for prompt injection — 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 per call at https://api.youraitools.co/injectscan/v1/scan)…