# ShieldAPI MCP Server Trust Score

> ShieldAPI MCP Server Trust Score is a paid API for AI agents from shield.vainplex.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

Checks the trust score of an MCP (Model Context Protocol) server endpoint before an AI agent connects to or calls it

## Facts

- Endpoint: POST https://shield.vainplex.dev/api/cdp/check-mcp-trust
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/shieldapi-mcp-server-trust-score-d09ef472
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_8AxJVC8_ev00MN_CFcXmT

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability shieldapi-mcp-server-trust-score-d09ef472 -d '<json body>'
```

Example prompt: Before connecting to that MCP server at https://tools.example.com/mcp, can you run a trust score check on it to make sure it's safe to call?

## When to prefer this

Use this endpoint specifically when an AI agent needs to evaluate whether an MCP (Model Context Protocol) server is trustworthy before connecting to it, installing it, or routing tool calls through it. This is the right choice when the subject being checked is an MCP server URL — as opposed to general domain trust, IP reputation, identity checks, or dependency scanning, which are covered by sibling ShieldAPI endpoints.

## Known failure modes

- Invalid or unreachable MCP server URL returns an error or low-confidence score
- Malformed input missing required 'endpoint' query parameter triggers validation error
- Unknown or newly registered MCP server may return low trust score due to lack of signal
- Network timeout if the MCP server endpoint is unresponsive during analysis
- Payment failure (x402) if USDC balance is insufficient for the $0.02 per-call fee

## How this service works

ShieldAPI - MCP Server Trust Score

## Output

Returns a trust score and risk assessment for the specified MCP server endpoint, indicating whether it is safe for an AI agent to connect to or invoke, along with supporting evidence or signals used to compute the score.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "endpoint"
     ],
     "properties": {
      "endpoint": {
       "type": "string",
       "description": "URL of the MCP server endpoint"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/shieldapi-mcp-server-trust-score-d09ef472/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from shield.vainplex.dev](https://www.zero.xyz/host/shield.vainplex.dev/llms.txt)