← all agents · MCP trust index
Limitguard Trust Intelligence
Limitguard is a KYB, sanctions/PEP and entity-trust API for AI agents and developers: it checks a company against business registers (KVK, KBO/CBE), VIES VAT, OpenSanctions, its domain and country risk, is paid per call with x402 (USDC) or an API key, is also served as an MCP server, and is hosted i
Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-09-29T22:19:00Z, first seen 2026-08-26T02:45:24Z). Not self-submitted, not cached from a directory.
Measured card surface
| field | value |
|---|---|
| A2A endpoint | https://api.limitguard.ai/a2a |
| card source | https://api.limitguard.ai/.well-known/agent-card.json |
| protocolVersion | 0.3.0 |
| agent version | 1.0 |
| preferredTransport | JSONRPC |
| provider | Limitguard |
| skills published | 3 |
| card hash (canonical) | 458d99b5d79531ad |
Interface URLs
| transport | URL |
|---|---|
| JSONRPC | https://api.limitguard.ai/a2a |
Skills (from card)
| skill | description |
|---|---|
| entity_check | Full entity trust check across up to 8 data sources, depending on the identifiers supplied. Returns trust score 0-100, cluster, and recommendation. |
| risk_score | Quick risk score assessment. Faster than full entity check. |
| kyb_check | Know Your Business verification with sanctions check and company registration. |
Card-drift history
Watching this agent since 2026-08-26T02:45:24Z. Hash = SHA-256 (16 hex)
of the card's canonical JSON (sort_keys, no whitespace), so whitespace-only
edits don't count as drift. Feed:
api/a2a-drift.json.
| when (UTC) | what | version | skills | hash was | hash now |
|---|---|---|---|---|---|
| 2026-09-26T11:59:55Z | changed | 1.0→1.0 | 3→3 | d45eae08fa | 458d99b5d7 |
| 2026-09-24T15:52:25Z | changed | 1.0→1.0 | 3→3 | b2e9b63224 | d45eae08fa |
| 2026-09-24T08:17:39Z | changed | 1.0→1.0 | 3→3 | 7bf37f6fa6 | b2e9b63224 |
| 2026-09-24T06:30:44Z | changed | 1.0→1.0 | 3→3 | 7d0ae7bedd | 7bf37f6fa6 |
| 2026-09-24T04:46:17Z | changed | 1.0→1.0 | 3→3 | 68776ea17f | 7d0ae7bedd |
| 2026-09-24T03:00:20Z | changed | 1.0→1.0 | 3→3 | e648170877 | 68776ea17f |
| 2026-09-23T20:23:43Z | changed | 1.0→1.0 | 3→3 | bf50df29bf | e648170877 |
| 2026-09-18T00:56:32Z | changed | 1.0→1.0 | 4→3 | 17c38a6812 | bf50df29bf |
| 2026-09-08T08:50:50Z | changed | 1.0→1.0 | 4→4 | c3dd2eb725 | 17c38a6812 |
| 2026-09-06T13:16:08Z | changed | 1.0→1.0 | 4→4 | 75ab5f4984 | c3dd2eb725 |
Same host, MCP side
Endpoints on this host that also appear in the official MCP registry, with their live trust grades — one host, two protocols, measured independently.
| MCP endpoint | grade | MCP OK | auth |
|---|---|---|---|
| https://api.limitguard.ai/mcp | A | ✓ | open |
Golemreach Trust Layer · A2A index · method & opt-out · card re-fetched every sweep round; opt-out per /trust/bot removes the whole host within 48h.