# LimitGuard Full Entity Trust Check (MCP)

> LimitGuard Full Entity Trust Check (MCP) is a paid API for AI agents from api.limitguard.ai, paid per call via x402, $0.85/call, status unknown (last checked 2026-10-12).

Performs a full entity trust check via MCP-native interface, returning a trust score, cluster assignment, and approval recommendation for a named legal entity.

## Facts

- Endpoint: POST https://api.limitguard.ai/v1/mcp/check-entity?utm_source=zero.xyz
- Price: $0.85/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/limitguard-full-entity-trust-check-mcp-bfb5658a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_jjCUXC2P6vWxQM36SQwUk

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 limitguard-full-entity-trust-check-mcp-bfb5658a -d '<json body>'
```

Example prompt: Can you run a full trust check on Acme Logistics B.V. in the Netherlands — their KVK number is 12345678 and domain is acmelogistics.nl — and tell me whether we should approve them?

## When to prefer this

Use this endpoint when you need a comprehensive, MCP-native full trust check on a legal entity — including sanctions, PEP, adverse media, and registration data — particularly for EU/Dutch entities where KVK number enrichment is available. Prefer this over the quick-score endpoint when you need cluster assignment and a formal APPROVE/REJECT recommendation rather than just a lightweight risk score.

## Known failure modes

- Missing required fields (entity_name or country) returns 400 Bad Request
- Unknown or unverifiable entity may return low trust score with REJECT recommendation
- Invalid KVK number format may cause lookup failure
- Payment not completed (x402) results in 402 Payment Required before processing
- Rate limiting or quota exhaustion returns 429 Too Many Requests

## How this service works

MCP tool: entity trust check for LLM agents. Runs the /v1/entity/check engine on entity_name, country, kvk_number and domain only, so up to 5 sources (no IBAN, VAT or wallet).

## Output

Returns a trust score (0-100), a cluster label (e.g. 'verified'), and a recommendation string (e.g. 'APPROVE' or 'REJECT') indicating whether the entity passed the full trust assessment.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "domain": {
   "type": "string",
   "description": "Entity website domain"
  },
  "country": {
   "type": "string",
   "description": "ISO country code (NL, BE, etc.)"
  },
  "kvk_number": {
   "type": "string",
   "description": "Dutch KVK number"
  },
  "entity_name": {
   "type": "string",
   "description": "Full legal name of the entity"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "cluster": "verified",
  "trust_score": 87,
  "recommendation": "APPROVE"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/limitguard-full-entity-trust-check-mcp-bfb5658a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.limitguard.ai](https://www.zero.xyz/host/api.limitguard.ai/llms.txt)