# AgentsTools MCP Security Scanner

> AgentsTools MCP Security Scanner is a paid API for AI agents from api.agentstools.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-13).

Performs a static security scan of an MCP manifest or tool list, returning a 0-100 risk score and per-tool findings covering prompt injection, tool poisoning, hidden unicode, data exfiltration, and rug-pull drift.

## Facts

- Endpoint: POST https://api.agentstools.dev/mcp/scan
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentstools-mcp-security-scanner-d29333a7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ks_Ppuzw2yGV54rotPrnx

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 agentstools-mcp-security-scanner-d29333a7 -d '<json body>'
```

Example prompt: Scan this MCP manifest for security threats — check for prompt injection, hidden unicode, tool poisoning, and data exfiltration directives, and give me a risk score and per-tool findings.

## When to prefer this

Choose this endpoint when you need a fast, automated static security analysis of MCP tool manifests or tool lists before deploying or integrating third-party agent tools. It is specifically designed for MCP/agent-tool security scenarios including rug-pull drift detection via hash pinning, which generic code scanners or LLM-based reviews do not provide. Prefer it over manual review when you need a quantified, reproducible 0-100 risk score with per-tool breakdown.

## Known failure modes

- Missing required 'input' field returns validation error
- Invalid body type or HTTP method enum value causes 400
- Malformed or non-object manifest/tools array results in parse error
- Empty tools list may return no findings but still consumes the $0.01 fee
- Network timeout if manifest is extremely large
- known_hashes with mismatched keys silently skips drift detection for unmatched tools

## 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 security findings (covering prompt injection, hidden unicode, tool poisoning, data exfiltration directives, dangerous capabilities, tool shadowing, and rug-pull drift), and content hashes for each tool. Results are security indicators, 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/agentstools-mcp-security-scanner-d29333a7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.agentstools.dev](https://www.zero.xyz/host/api.agentstools.dev/llms.txt)