{"data":{"name":"io.github.agentgate-builder/x402-prompt-injection-scan","title":"InjectScan","description":"Prompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools","version":"0.1.0","websiteUrl":"https://injectscan.agentgate.workers.dev","repositoryUrl":"https://github.com/agentgate-builder/x402-prompt-injection-scan","remotes":[{"url":"https://injectscan.agentgate.workers.dev/mcp","type":"streamable-http"}],"packages":[],"status":"active","isLatest":true,"publishedAt":"2026-10-21T22:01:49.509Z","updatedAt":"2026-10-21T22:01:49.509Z","source":"official-registry","verification":"official","confidence":100,"stars":null,"sources":[{"stars":null,"title":"InjectScan","source":"official-registry","sourceId":"io.github.agentgate-builder/x402-prompt-injection-scan","updatedAt":"2026-10-21T22:01:49.509Z","confidence":100,"websiteUrl":"https://injectscan.agentgate.workers.dev","description":"Prompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools","verification":"official","repositoryUrl":"https://github.com/agentgate-builder/x402-prompt-injection-scan"}],"toolIndex":{"tools":[{"serverName":"io.github.agentgate-builder/x402-prompt-injection-scan","endpointFingerprint":"d245cc567031cee83cdfd3935a8926051f95d20019cac89dff27c1b00bc90579","name":"scan_text","title":"Scan text for prompt injection","description":"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.","inputSchema":{"type":"object","properties":{"text":{"type":"string","description":"The untrusted text to scan, as one plain string (1-100000 characters; longer text is truncated and flagged). Offsets in findings refer to this string."}},"required":["text"]},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false},"definitionHash":"f27c90755a5eb7569e2ced6da1639a0838d05af280983cd9c1159cfd7090e04c","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-10-31T18:46:41.492Z","metadataTrust":"untrusted"},{"serverName":"io.github.agentgate-builder/x402-prompt-injection-scan","endpointFingerprint":"d245cc567031cee83cdfd3935a8926051f95d20019cac89dff27c1b00bc90579","name":"scan_tools","title":"Scan MCP tool definitions for tool poisoning","description":"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.","inputSchema":{"type":"object","properties":{"tools":{"type":"array","items":{"type":"object"},"description":"1-100 tool definitions as objects {name, description, inputSchema} (as returned by an MCP server's tools/list; input_schema or parameters are also read). Every string field, including nested schema descriptions, is scanned."}},"required":["tools"]},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false},"definitionHash":"a8d68c8c1d00d97b7b5b9847228fcb80697c3d2a5a3971a379b7949e8db5553f","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-10-31T18:46:41.492Z","metadataTrust":"untrusted"},{"serverName":"io.github.agentgate-builder/x402-prompt-injection-scan","endpointFingerprint":"d245cc567031cee83cdfd3935a8926051f95d20019cac89dff27c1b00bc90579","name":"scan_url","title":"Fetch a web page and scan it for prompt injection","description":"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.","inputSchema":{"type":"object","properties":{"url":{"type":"string","description":"Absolute http:// or https:// URL of a public web page, e.g. \"https://example.com/post\". Private, loopback and internal hosts are refused; robots.txt is respected."}},"required":["url"]},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true},"definitionHash":"d4778fd75480b79cd5c2d2e97ffef6bbd168c2a9ba9212d3e08a442313d937c0","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-10-31T18:46:41.492Z","metadataTrust":"untrusted"}],"endpoints":[{"endpointFingerprint":"d245cc567031cee83cdfd3935a8926051f95d20019cac89dff27c1b00bc90579","protocol":"streamable-http","status":"indexed","toolCount":3,"observedAt":"2026-10-31T18:46:41.492Z"}],"authentication":"unknown"},"connectionConfigurations":{"status":"ready","authentication":"not embedded","clients":{"Claude Desktop":{"mcpServers":{"io.github.agentgate-builder/x402-prompt-injection-scan":{"url":"https://injectscan.agentgate.workers.dev/mcp"}}},"Cursor":{"mcpServers":{"io.github.agentgate-builder/x402-prompt-injection-scan":{"url":"https://injectscan.agentgate.workers.dev/mcp"}}},"VS Code":{"servers":{"io.github.agentgate-builder/x402-prompt-injection-scan":{"type":"http","url":"https://injectscan.agentgate.workers.dev/mcp"}}}}},"resourceType":"mcp-server","callable":true,"runtime":{"callable":true,"protocols":["mcp"]},"interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://injectscan.agentgate.workers.dev/mcp"}],"profile":{"apiVersion":"1","schemaVersion":"1","id":"mcp-server:io.github.agentgate-builder%2Fx402-prompt-injection-scan","resourceType":"mcp-server","canonicalUrl":"https://www.agentsjunction.com/api/v1/servers/io.github.agentgate-builder%2Fx402-prompt-injection-scan","name":"io.github.agentgate-builder/x402-prompt-injection-scan","description":"Prompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools","interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://injectscan.agentgate.workers.dev/mcp"}],"capabilities":[],"identity":{"source":"official-registry","websiteUrl":"https://injectscan.agentgate.workers.dev","repositoryUrl":"https://github.com/agentgate-builder/x402-prompt-injection-scan","version":"0.1.0"},"verification":{"state":"official","confidence":100},"operations":{"resourceType":"mcp-server","name":"io.github.agentgate-builder/x402-prompt-injection-scan","status":"online","lastCheckedAt":"2026-11-03T18:16:13.575Z","lastSuccessfulCheck":"2026-11-03T18:16:13.575Z","latencyMs":227,"consecutiveFailures":0,"isStale":false,"checks":{"endpointReachable":true,"protocolValid":true,"agentCardValid":null,"mcpHandshakeValid":true},"lastSeen":null,"lastSuccessfulInteraction":null,"lastHealthCheck":"2026-11-03T18:16:13.575Z","source":{"type":"health-check","url":null},"observedAt":"2026-11-03T18:16:13.575Z"},"security":null,"timestamps":{"createdAt":"2026-10-21T22:01:49.509Z","updatedAt":"2026-10-21T22:01:49.509Z","observedAt":"2026-11-03T18:16:13.575Z"},"compatibility":{"serverVersion":"0.1.0","protocolVersions":[{"protocol":"mcp","version":null}]}}}}