# Grey Ridge Signals — MCP Security Scanner (x402)

> Grey Ridge Signals — MCP Security Scanner (x402) is a paid API for AI agents from x402-data-api.sigrunner.workers.dev, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-14).

Scans an MCP server URL for security vulnerabilities including tool-poisoning and hidden instructions, returning a risk score and categorized findings

## Facts

- Endpoint: GET https://x402-data-api.sigrunner.workers.dev/scan/mcp
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/grey-ridge-signals-mcp-security-scanner-x402-9d00fbee
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_NIqUmMx9QfIvcXVMGm6lz

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 grey-ridge-signals-mcp-security-scanner-x402-9d00fbee
```

Example prompt: Can you scan https://example.com/mcp for security issues and tell me if any of its tools have hidden instructions or poisoning risks before I connect to it?

## When to prefer this

Use this endpoint when you need to programmatically verify the safety of an MCP server before connecting an AI agent to it — especially to detect tool-poisoning, hidden prompt injection, or malicious instructions embedded in tool definitions. Prefer it over manual inspection when you need a structured risk score and machine-readable findings for automated pipelines. It requires no API key and charges $0.10 USDC per scan via x402 on Base.

## Known failure modes

- Target URL is unreachable or returns non-MCP responses — scan may fail or return empty findings
- Invalid or malformed target URL results in an error response
- MCP server requires authentication that the scanner cannot satisfy, limiting tool discovery
- x402 payment failure if USDC balance is insufficient or Base network is congested
- Rate limiting if the same target is scanned repeatedly in quick succession

## How this service works

Agent-native pay-per-call data on Base (USDC via x402). No API keys, no signup. Discovery: /.well-known/x402

## Output

Returns a JSON object with: the scanned target URL, a verdict (e.g. 'review' or 'pass'), an array of findings each with rule name, affected tool, detail, evidence, and severity (critical/high/medium/low), an overall risk_score (0–100), a human-readable risk_summary, and the count of tools_scanned.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "properties": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "target": "https://example.com/mcp",
  "verdict": "review",
  "findings": [
   {
    "rule": "tool-poisoning:hidden-instructions",
    "tool": "read_file",
    "detail": "…",
    "evidence": "…",
    "severity": "critical"
   }
  ],
  "risk_score": 40,
  "risk_summary": "1 issue across 3 tools, 1 CRITICAL (tool-poisoning). Risk 40/100.",
  "tools_scanned": 3
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/grey-ridge-signals-mcp-security-scanner-x402-9d00fbee/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-data-api.sigrunner.workers.dev](https://www.zero.xyz/host/x402-data-api.sigrunner.workers.dev/llms.txt)