{"name":"Agent Safe","description":"11-tool message security suite for AI agents (8 paid + 3 free). Protects against phishing, BEC, malware, social engineering, manipulation, AI-generated images, deepfakes, and prompt injection across any message (emails, chats, DMs, SMS), URLs, replies, threads, attachments, sender identities, and media. Start with the free assess_message tool to get personalized recommendations, query check_prompt_injection_db for known injection patterns, and use submit_feedback to report results.","version":"2.4.0","protocol":"mcp","transport":{"type":"streamable-http","url":"https://agentsafe.locationledger.com/mcp"},"authentication":{"type":"header","header_name":"skyfire-api-key","description":"Skyfire Buyer API Key for payment. Get one at skyfire.xyz. $0.01 per unit. Alternatively, send a PAY token via skyfire-pay-id header."},"tools":[{"name":"check_email_safety","description":"Analyze an email for phishing, social engineering, prompt injection, CEO fraud, and data exfiltration. Returns verdict, risk score, threats, and actions."},{"name":"check_url_safety","description":"Analyze URLs for phishing, malware, redirects, spoofing, and tracking. Returns per-URL and overall verdicts."},{"name":"check_response_safety","description":"Check a draft reply BEFORE sending for data leakage, social engineering compliance, and unauthorized disclosure."},{"name":"analyze_email_thread","description":"Analyze a full email thread for escalating social engineering, scope creep, and manipulation patterns."},{"name":"check_attachment_safety","description":"Assess attachments for malware risk based on filename, MIME type, and size BEFORE opening."},{"name":"check_sender_reputation","description":"Verify sender identity with live DNS DMARC and RDAP domain age checks. Detects BEC and impersonation."},{"name":"check_message_safety","description":"Analyze non-email messages (SMS, WhatsApp, Instagram DMs, Discord, Slack, etc.) for platform-specific threats like smishing, wrong-number scams, and OTP interception."},{"name":"check_media_authenticity","description":"Analyze images and short videos to assess whether they are AI-generated, deepfaked, or authentic. Uses multi-layer forensic analysis. $0.04/image, $0.10/video."},{"name":"check_prompt_injection_db","description":"FREE — Query a database of known prompt injection attacks observed in the wild on agent social networks. Returns recent patterns, payloads, and classifications."},{"name":"assess_message","description":"FREE triage tool — send whatever context you have and get a prioritized list of which security tools to run. No charge, instant response. Call this first."},{"name":"submit_feedback","description":"FREE — Submit feedback about any Agent Safe tool you used. No charge, no auth required."}],"pricing":{"model":"per_unit","unit_amount":"0.01","currency":"USD","note":"Most tools: 1 unit ($0.01). Image analysis: 4 units ($0.04). Video analysis: 10 units ($0.10).","payment_network":"Skyfire"},"contact":"support@locationledger.com","legal":"https://agentsafe.locationledger.com/terms","homepage":"https://agentsafe.locationledger.com","repository":"https://github.com/wowcool/Agent-Safe-MCP"}