Koskamo

Veredicto Humano MCP

An MCP server that allows AI agents to ask a real human for subjective or cultural judgments, specialized in the Argentine context, by paying $0.10 USDC via x402 on Base. It provides tools to create verdict tickets and poll for results asynchronously.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Veredicto Humano MCP logo, by GabrielCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by Gabriel
MCP endpoint (Streamable HTTP)
https://veredictohumano.com/mcp
Vendor documentation

What its tools do

2 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (1)

Can change data (1)

2 of 2 have a description · 2 of 2 declare behavior hints · 2 of 2 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Check if Spanish text sounds natural to an Argentine
  • Identify if an ad looks like a typical local scam
  • Verify if the tone is right for a chatbot

Source and maintenance

Community listingRegistry 1.0.3
Maintenance checked

Protocol and capabilities

Server
veredicto-humano-x402 1.0.3
MCP protocol negotiated in check
2025-11-25
Tools
2 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Tools

2 advertised

ask_human_verdict — Pedir el veredicto de una persona real
Advertised by the server during the last successful anonymous check.
Open-world

Pagá $0.10 USDC en Base por el juicio subjetivo/cultural de una persona real (no un LLM) sobre una pregunta — especializado en contexto argentino. Sin pago adjunto devuelve los requisitos de pago x402; con el pago, crea el ticket y devuelve {ticket, resultToken, poll}. La respuesta del humano llega de forma asíncrona (minutos u horas) y vuelve a vos, el agente, por get_human_verdict: no llega por Telegram (Telegram es solo cómo la persona recibe la pregunta).

ask_human_verdict input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "question"
  ],
  "properties": {
    "labels": {
      "type": "string",
      "description": "CSV de 2-6 respuestas categóricas posibles, ej. \"natural,traducido\""
    },
    "context": {
      "type": "string",
      "maxLength": 2000,
      "description": "Contexto extra que ve el humano"
    },
    "question": {
      "type": "string",
      "maxLength": 500,
      "minLength": 1,
      "description": "La pregunta de juicio subjetivo"
    }
  },
  "additionalProperties": false
}
ask_human_verdict output schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "status",
    "ticket",
    "resultToken",
    "poll",
    "expiresAt"
  ],
  "properties": {
    "poll": {
      "type": "string",
      "format": "uri",
      "description": "URL equivalente para pollear por HTTP"
    },
    "status": {
      "type": "string",
      "const": "pending",
      "description": "Siempre \"pending\": la persona todavía no respondió"
    },
    "ticket": {
      "type": "string",
      "format": "uuid",
      "description": "Id del ticket, para get_human_verdict"
    },
    "expiresAt": {
      "type": "string",
      "description": "Cuándo vence el ticket si nadie responde (ISO 8601)"
    },
    "resultToken": {
      "type": "string",
      "description": "Secreto para leer el resultado, guardalo"
    }
  },
  "additionalProperties": false
}
ask_human_verdict annotations
{
  "title": "Pedir el veredicto de una persona real",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
get_human_verdict — Consultar el resultado de un veredicto pedido
Advertised by the server during the last successful anonymous check.
Advertised read-only

Gratis. Pollea el estado de un ticket creado con ask_human_verdict — "pending" mientras la persona todavía no contestó, "completed" con el veredicto, o "expired" si pasaron 7 días sin respuesta.

get_human_verdict input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "ticket",
    "resultToken"
  ],
  "properties": {
    "ticket": {
      "type": "string",
      "format": "uuid",
      "description": "El ticket devuelto por ask_human_verdict"
    },
    "resultToken": {
      "type": "string",
      "minLength": 1,
      "description": "El resultToken devuelto por ask_human_verdict"
    }
  },
  "additionalProperties": false
}
get_human_verdict output schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "status",
    "ticket"
  ],
  "properties": {
    "panel": {
      "type": "object",
      "required": [
        "type",
        "responses"
      ],
      "properties": {
        "type": {
          "type": "string",
          "const": "single-trusted-human"
        },
        "responses": {
          "type": "number",
          "const": 1
        }
      },
      "description": "Solo en \"completed\": una única persona de confianza, no un promedio anónimo",
      "additionalProperties": false
    },
    "status": {
      "enum": [
        "pending",
        "completed",
        "expired"
      ],
      "type": "string"
    },
    "ticket": {
      "type": "string",
      "format": "uuid"
    },
    "verdict": {
      "type": [
        "string",
        "null"
      ],
      "description": "Solo en \"completed\": la etiqueta elegida, si hubo"
    },
    "freeText": {
      "type": [
        "string",
        "null"
      ],
      "description": "Solo en \"completed\": el comentario libre, si hubo"
    },
    "expiredAt": {
      "type": "string",
      "description": "Solo en \"expired\""
    },
    "expiresAt": {
      "type": "string",
      "description": "Solo en \"pending\""
    },
    "answeredAt": {
      "type": "string",
      "description": "Solo en \"completed\""
    }
  },
  "additionalProperties": false
}
get_human_verdict annotations
{
  "title": "Consultar el resultado de un veredicto pedido",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
340 ms
95th percentile latency
340 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 340 ms · metadata changed · 2 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http veredicto-humano-mcp https://veredictohumano.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add veredicto-humano-mcp --url https://veredictohumano.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable veredicto-humano-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "veredicto-humano-mcp": {
      "url": "https://veredictohumano.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "veredicto-humano-mcp": {
      "type": "streamableHttp",
      "url": "https://veredictohumano.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start veredicto-humano-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "veredicto-humano-mcp": {
      "type": "http",
      "url": "https://veredictohumano.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http veredicto-humano-mcp https://veredictohumano.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://veredictohumano.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "veredicto-humano-mcp": {
      "serverUrl": "https://veredictohumano.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Veredicto Humano MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.