# PayAI MCP Security Scanner

> PayAI MCP Security Scanner is a paid API for AI agents from payai.agentstools.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-16).

Statically scans an MCP manifest or tool list for security threats including tool poisoning, prompt injection, hidden unicode, data-exfiltration directives, tool shadowing, and rug-pull drift, returning a 0-100 risk score with per-tool findings.

## Facts

- Endpoint: POST https://payai.agentstools.dev/mcp/scan
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/payai-mcp-security-scanner-b2004ad2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_K1DVDRE21WFd2GUjC4uMh

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 payai-mcp-security-scanner-b2004ad2 -d '<json body>'
```

Example prompt: Can you run a security scan on this MCP manifest and tell me the risk score and what specific threats were found — I want to know if there's any prompt injection, tool shadowing, or hidden unicode before I connect it to my agent?

## When to prefer this

Use this endpoint when you need to statically audit an MCP manifest or tool list before connecting it to an AI agent, or when verifying that a previously approved manifest hasn't drifted. It is purpose-built for MCP-specific threats like tool shadowing and rug-pull drift that generic security scanners don't cover. Prefer it over manual review or generic linters when you want a structured risk score and per-tool findings with content hashes for change tracking.

## Known failure modes

- Malformed or unparseable MCP manifest returns validation error
- Empty tool list may return minimal findings with no meaningful score
- Very large manifests may time out or be truncated
- Obfuscated or encoded payloads may evade static detection
- Novel attack patterns not in the detection ruleset may be missed

## How this service works

Static security scan of an MCP manifest or tool list. Detects tool poisoning, hidden unicode instructions, prompt injection, data-exfiltration directives, dangerous capabilities, tool shadowing and post-approval rug-pull drift. Returns a 0-100 risk score, category, per-tool findings and content hashes. Security indicators, not a guarantee.

## Output

Returns a 0-100 risk score, a risk category label, per-tool findings listing detected threats (tool poisoning, hidden unicode, prompt injection, data-exfiltration, dangerous capabilities, tool shadowing, rug-pull drift), and SHA content hashes for each tool. Results are security indicators and not a guarantee of safety.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "tools": {
   "type": "array",
   "items": {
    "type": "object"
   },
   "description": "Alternatively, a list of tool objects (name, description, inputSchema)"
  },
  "manifest": {
   "type": "object",
   "description": "MCP manifest object (with a tools list) or a single tool object"
  },
  "known_hashes": {
   "type": "object",
   "description": "Optional map of tool name to a previously pinned tool_hash, to detect rug-pull drift"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/payai-mcp-security-scanner-b2004ad2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from payai.agentstools.dev](https://www.zero.xyz/host/payai.agentstools.dev/llms.txt)