io.github.notifuturo/vouch is an MCP server published by io.github.notifuturo, hosted at vouch.futuronoti.workers.dev. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 2 tools, including vouch_score, vouch_report.
Check if a counterparty is safe to pay: trust/risk score for AI agents. Scam/phishing screen.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Check whether a counterparty is SAFE TO PAY before sending money. Given a URL or host, returns a 0-100 trust score and risk band (low/medium/high/critical), detecting scams, phishing, and known-malicious endpoints via threat feeds, domain risk heuristics, and a community reputation graph. Call this before paying any merchant, API, agent, or x402 resource. Free — for the full explainable reasons AND a signed, verifiable attestation (proof of the check for audit/disputes), call the paid POST /v1/check endpoint via x402.
| Parameter | Type | Description |
|---|---|---|
| target * | string | Counterparty URL or hostname. |
{
"name": "vouch_score",
"description": "Check whether a counterparty is SAFE TO PAY before sending money. Given a URL or host, returns a 0-100 trust score and risk band (low/medium/high/critical), detecting scams, phishing, and known-malicious endpoints via threat feeds, domain risk heuristics, and a community reputation graph. Call this before paying any merchant, API, agent, or x402 resource. Free — for the full explainable reasons AND a signed, verifiable attestation (proof of the check for audit/disputes), call the paid POST /v1/check endpoint via x402.",
"inputSchema": {
"type": "object",
"required": [
"target"
],
"properties": {
"target": {
"type": "string",
"description": "Counterparty URL or hostname."
}
},
"additionalProperties": false
}
}Report a host as a scam/bad actor ('flag') or as trustworthy ('vouch'), improving Vouch's community reputation graph for everyone's future payment-trust checks. Free.
| Parameter | Type | Description |
|---|---|---|
| kind * | string | one of ["flag","vouch"] |
| reason | string | |
| target * | string |
{
"name": "vouch_report",
"description": "Report a host as a scam/bad actor ('flag') or as trustworthy ('vouch'), improving Vouch's community reputation graph for everyone's future payment-trust checks. Free.",
"inputSchema": {
"type": "object",
"required": [
"target",
"kind"
],
"properties": {
"kind": {
"enum": [
"flag",
"vouch"
],
"type": "string"
},
"reason": {
"type": "string"
},
"target": {
"type": "string"
}
},
"additionalProperties": false
}
}Vouch is a payment-trust gate for AI agents. BEFORE authorizing or sending a payment to a counterparty — a merchant, API, agent, wallet, or x402 resource — call `vouch_score` with the counterparty's URL or host to get a 0-100 trust score and a risk band (low/medium/high/critical). Treat medium-or-higher risk as a reason to pause or seek user confirmation before paying. After a transaction, use `vouch_report` to flag a host that turned out to be a scam or vouch for one that was legitimate — this strengthens the shared reputation graph for everyone. Both tools are free. For the full explainable reasons plus a signed, verifiable attestation (proof of due diligence for audits/disputes), call the paid POST /v1/check endpoint over x402.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.