agent-verified-relay

Viridis Verified: wrap any MCP server with tamper-evident delivery receipts + metered fees.

Should I use this

Quality & Safety

B
Description quality
90%
Schema completeness
64%
Naming quality
91%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (1)

  • LOWTool 'describe_agent' description lacks action verbin describe_agent

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~898Tokens (tool definitions)
~1.1 KBTypical response size
Moderate attention impact (0.70% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "agent-verified-relay": {
      "url": "https://mcp.viridisconservation.com/verified/mcp"
    }
  }
}

Remote endpoints

https://mcp.viridisconservation.com/verified/mcpstreamable-http

What it can do

Tool inventory

Tools (7)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
⚪register_service(url, provider, description, fee_minor, payment_ref, ...)

Register a third-party MCP server (https, public FQDN only) under Viridis Verified. Returns a content-addressed service_id; idempotent on (url, provider). fee_minor is the per-verified-call fee in cents.

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "title": "Url",
      "type": "string"
    },
    "provider": {
      "title": "Provider",
      "type": "string"
    },
    "description": {
      "default": "",
      "title": "Description",
      "type": "string"
    },
    "fee_minor": {
      "default": 2,
      "title": "Fee Minor",
      "type": "integer"
    },
    "payment_ref": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Payment Ref"
    },
    "request_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Request Id"
    }
  },
  "required": [
    "url",
    "provider"
  ],
  "title": "register_serviceArguments"
}

Output Schema

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "register_serviceOutput"
}
⚪call_verified(service_id, tool, call_id, arguments, timeout_s, ...)

Relay a tools/call to a registered MCP service and notarize the exchange: request hash + response hash + outcome land in a tamper-evident receipt chain. Idempotent on call_id (a replay returns the original receipt and cached result — the downstream is never double-called). Failures are receipted evidence, not silence.

Input Schema

{
  "type": "object",
  "properties": {
    "service_id": {
      "title": "Service Id",
      "type": "string"
    },
    "tool": {
      "title": "Tool",
      "type": "string"
    },
    "call_id": {
      "title": "Call Id",
      "type": "string"
    },
    "arguments": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Arguments"
    },
    "timeout_s": {
      "default": 20,
      "title": "Timeout S",
      "type": "integer"
    },
    "payment_ref": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Payment Ref"
    },
    "request_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Request Id"
    }
  },
  "required": [
    "service_id",
    "tool",
    "call_id"
  ],
  "title": "call_verifiedArguments"
}

Output Schema

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "call_verifiedOutput"
}
🟢get_receipt(receipt_id)

Fetch a single delivery receipt by id.

Input Schema

{
  "type": "object",
  "properties": {
    "receipt_id": {
      "title": "Receipt Id",
      "type": "string"
    }
  },
  "required": [
    "receipt_id"
  ],
  "title": "get_receiptArguments"
}

Output Schema

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "get_receiptOutput"
}
⚪verify_receipts(service_id)

Recompute a service's full receipt hash chain and fee ledger. Any party can audit Viridis Verified from receipts alone.

Input Schema

{
  "type": "object",
  "properties": {
    "service_id": {
      "title": "Service Id",
      "type": "string"
    }
  },
  "required": [
    "service_id"
  ],
  "title": "verify_receiptsArguments"
}

Output Schema

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "verify_receiptsOutput"
}
🟢list_services

List registered services with call/fee counters.

Input Schema

{
  "type": "object",
  "properties": {},
  "title": "list_servicesArguments"
}

Output Schema

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "list_servicesOutput"
}
⚪service_stats(service_id)

Call counts, error counts, and accrued fees for one service.

Input Schema

{
  "type": "object",
  "properties": {
    "service_id": {
      "title": "Service Id",
      "type": "string"
    }
  },
  "required": [
    "service_id"
  ],
  "title": "service_statsArguments"
}

Output Schema

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "service_statsOutput"
}
🟢describe_agent

Fleet-standard self-description.

Input Schema

{
  "type": "object",
  "properties": {},
  "title": "describe_agentArguments"
}

Output Schema

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "describe_agentOutput"
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded7 tools
verifiedversion not recorded7 tools