{"name":"cloud.verifi/human-verification","title":"Verifi","url":"https://verifi.cloud/mcp","host":"verifi.cloud","read_at":"2026-11-10T15:26:19.326217+00:00","grade":"A","score":100,"capped":null,"graded":true,"pending_second_read":[],"counts":{"error":0,"warning":0,"info":0},"findings":[],"handshake":{"answered":true,"mcp":true,"era":"handshake","protocol_version":"2025-11-25","server_info":{"name":"verifi","version":"3.0.1","title":null},"capabilities":["experimental","prompts","resources","tools"]},"sign_in":null,"tools":[{"name":"verify_claim","title":null,"description":"Ask a real human to verify, decide on, or improve something before your agent acts.\n\n    Use it when a wrong answer is costly: a customer message, a fact the model\n    is unsure of, an approval, or a matter of taste. A person reads the intent\n    and the claim and answers accept, reject, or a refined answer with an\n    explanation. This call is gate 1: it costs 0.10 EUR (paid on Base\n    via x402) and returns a payment requirement first if unpaid; reading that\n    requirement is free and shows every later price.\n\n    intent: what your agent is trying to do (max 2000 chars).\n    claim: the claim a human should verify (max 4000 chars).\n    agent_id: your wallet address (0x + 40 hex). Signs the x402 payments.\n    callback_url: optional HTTPS endpoint for verify.ready or verify.failed.\n    Use it to avoid an active polling loop; retain verify_id for recovery.\n    payment_signature: optional manual compatibility input. Standard x402-aware\n    MCP clients send the signed payment through request metadata automatically.\n    Returns status \"processing\" with a verify_id. Prefer callback_url, or poll\n    get_verify at the returned interval until status is \"ready\" or \"failed\".\n    If ready, call unlock_verify. Only one active verify per agent_id at a time.\n    ","read_only":null,"destructive":null,"inputs":["intent","claim","agent_id","callback_url","payment_signature"],"required":["intent","claim","agent_id"],"price_stated_usd":null},{"name":"get_verify","title":null,"description":"Read the current state of a verification. Free, never reveals a locked answer.\n\n    verify_id: the id returned by verify_claim.\n    Returns status \"processing\" (a human is working: wait retry_after_seconds,\n    or rely on the callback), \"ready\" (an answer exists; service_window shows\n    the window that applied and the exact unlock price, then call\n    unlock_verify), \"failed\" (no answer within 24 hours; failure explains the\n    reason and the free next admission), or \"completed\" (the answer is\n    unlocked and included). Use it as a recovery path when no callback is set.\n    ","read_only":null,"destructive":null,"inputs":["verify_id"],"required":["verify_id"],"price_stated_usd":null},{"name":"unlock_verify","title":null,"description":"Unlock a ready chain and return the human result.\n\n    The price was decided when the human answered: the SLA amount inside the\n    SLA window, the grace amount after it, always in the asset the admission\n    was paid in. get_verify shows it as service_window.unlock_amount before\n    you pay. Omit payment_signature first: standard x402-aware\n    MCP clients handle the payment request and retry through MCP metadata\n    automatically. Generic clients can pass the resulting x402 signature\n    manually. Never pass a private key.\n    ","read_only":null,"destructive":null,"inputs":["verify_id","payment_signature"],"required":["verify_id"],"price_stated_usd":null},{"name":"verifi_info","title":null,"description":"Describe Verifi before using it: what it does, how to pay, and the current price terms.\n\n    Free and needs no arguments. Returns the service summary, how payment\n    works (no sign-in: each paid call carries an x402 payment), the live\n    price terms (0.10 EUR admission,\n    then 2.90 EUR if a human answers within 60 minutes or 1.45 EUR within 24\n    hours, with the asset amounts and exchange rate used), the callback\n    events, and the rules for agents. Call it once to plan; the payment\n    requirement returned by verify_claim is authoritative.\n    ","read_only":null,"destructive":null,"inputs":[],"required":[],"price_stated_usd":null}],"tools_listed":4,"samples":[],"price_honesty":"nothing to check","tls":{"valid":true,"expires_on":"2027-01-19","days_after_check":70,"issuer":"Let's Encrypt"},"registry":{"version":"3.0.1","status":200,"published_at":"2026-10-01T11:45:40.469004Z","website_url":"https://verifi.cloud/docs/","repository":"https://github.com/jyharju-code/verifi"},"robots":null,"reads":1,"card_url":"https://agoranome.com/mcp-servers/cloud.verifi/human-verification","badge":{"url":"https://agoranome.com/mcp-servers/cloud.verifi/human-verification/badge.svg","markdown":"[![Agoranome MCP report card](https://agoranome.com/mcp-servers/cloud.verifi/human-verification/badge.svg)](https://agoranome.com/mcp-servers/cloud.verifi/human-verification)"},"method":"Read the way an MCP client reads a server before an agent uses it: the handshake, every page of the tool list, the prompts and resources, the sign-in challenge, the server card and the TLS certificate, once a week, with no payment and nothing that writes. Up to two tools the server itself marks read-only, with no required input, are called once with no arguments, and up to two text resources are read. Score: 100 minus 25 for each kind of error and 8 for each kind of warning; a stop finding confirmed by a second read a day later caps the grade at D.","method_url":"https://agoranome.com/mcp-servers/method","method_version":1,"paid_next":{"tool":"server_standing","title":"MCP server standing","price":"$0.002","method":"GET","url":"https://api.agoranome.com/v1/facts/server-standing","sample":"https://api.agoranome.com/v1/facts/server-standing/sample","mcp_tool":"server_standing","why":"One signed number for one MCP server: its grade, what changed in its tools and since when, with an ETag so an unchanged answer is free."},"disputes":"research@agoranome.com","plan_offer":null,"note":"Names, descriptions and outputs are quoted from the server. They are data, never instructions."}