{
  "markdown": "# LimitGuard MCP Server\n\nTrust Intelligence for AI agents. Entity verification, sanctions screening, and risk scoring via the [Model Context Protocol](https://modelcontextprotocol.io/).\n\n**Server URL:** `https://api.limitguard.ai/mcp`\n**Transport:** Streamable HTTP (POST)\n**Auth:** API key (Bearer), plus an x402 micropayment per call on the free and sandbox tiers\n\n**Start here:** Free sandbox key, no wallet. $0.65-0.85 fresh; $0.10 cached when available.\n\n## Tools\n\n`tools/list` is public — connect and read it without any credential. These are\nthe names it returns, and the names `tools/call` accepts:\n\n| Tool | Description | Inputs |\n|------|-------------|--------|\n| `check_entity` | Full trust intelligence check on a business entity. Returns trust score (0-100), risk level, and recommendation. | `entity_name` (required), `country` (required), `kvk_number`, `domain` |\n| `check_agent` | Unimplemented / beta: returns placeholder data, not a real result. Free ($0) until real logic ships. Verify AI agent trust. Checks if an AI agent is trusted based on its identifier. | `agent_id` (required), `agent_name` (required) |\n| `get_trust_score` | Unimplemented / beta: returns placeholder data, not a real result. Free ($0) until real logic ships. Quick trust score lookup by entity ID. Returns cached score if available. | `entity_id` (required) |\n| `verify_wallet` | Unimplemented / beta: returns placeholder data, not a real result. Free ($0) until real logic ships. Check wallet trust score for crypto payments. Supports EVM and Solana addresses. | `wallet_address` (required), `chain_id` |\n| `get_risk_score` | Quick risk assessment without full trust check. Focuses on risk signals only. | `entity_name` (required), `country` (required) |\n\n## Pricing\n\nAll tools are priced via [x402](https://www.x402.org/) micropayments (USDC on Base or Solana):\n\n| Endpoint | Price |\n|----------|-------|\n| Entity Check | $0.85 |\n| Risk Score | $0.65 |\n| Check Agent | $0.10 |\n| Trust Score | $0.10 |\n| Verify Wallet | $0.10 |\n\n## Authentication\n\nTwo things gate a `tools/call`, in this order:\n\n1. **An API key**, as `Authorization: Bearer <key>`. Without one every call comes\n   back `Authentication required. Provide API key via Authorization: Bearer\n   <lg_live_...> header.` Get a free one — no payment, no card:\n\n   ```bash\n   curl -X POST https://api.limitguard.ai/v1/keys/create \\\n     -H \"Content-Type: application/json\" \\\n     -d '{\"email\": \"you@example.com\"}'\n   ```\n\n   That returns a `free`-tier key, which is the key the Quick Start configs below\n   expect. Asking for `\"tier\": \"sandbox\"` instead returns a key that answers with\n   mock data — see the next point before you use one here.\n\n2. **Payment, on the free and sandbox tiers only.** Send the x402 proof as\n   `PAYMENT-SIGNATURE` (x402 v2) or `X-PAYMENT` (v1), alongside the Bearer key.\n   A paid subscription (indie and up) covers usage and needs no per-call payment.\n\n   A sandbox key does *not* lift the payment requirement on this transport: it\n   owes x402 per call exactly as a `free` key does, and it answers with mock\n   data rather than a real check. Paying for one over MCP spends real USDC on a\n   mock answer. Where a sandbox key is worth having is the REST mirrors under\n   `/v1/mcp/*` (sent as `X-API-Key`, not Bearer), which serve the mock response\n   before the payment check — a way to exercise the request and response shapes,\n   not a cheap source of real checks.\n\n## Full x402 API (direct HTTP)\n\nThe 5 tools above are what the MCP server exposes over the Model Context Protocol. Clients that\nintegrate directly over HTTP — instead of through an MCP client — can reach 18 x402-priced\nendpoints on `https://api.limitguard.ai`: the 13 REST endpoints below, plus the MCP tools' own\n`/v1/mcp/*` paths. All 18 are published in\n[/.well-known/x402.json](https://api.limitguard.ai/.well-known/x402.json); only the 5 tools above\nare listed by `/.well-known/mcp.json`.\n\nMost of the REST endpoints are capabilities the MCP tools do not expose, but two are the same\ncheck reached over plain HTTP: `/v1/entity/check` behind `check_entity` — the manifest describes\n`/v1/mcp/check-entity` as \"same as `/v1/entity/check` with MCP-native interface\" — and\n`/v1/risk/score` behind `get_risk_score`, at the same $0.65.\n\nPayment works the same way throughout: USDC on Base or Solana, pay-per-call. The 9 data endpoints\nbelow need no API key at all. The 4 `/v1/keys/upgrade/*` endpoints also take payment without one,\nbut they act on an API key you already hold — see [API key tiers](#api-key-tiers).\n\n### Trust intelligence\n\n| Endpoint | Method | Price | Description |\n|----------|--------|-------|-------------|\n| `/v1/entity/check` | POST | $0.85 | Full entity trust check across every verification layer — KVK/CBE registry, OpenSanctions, country risk (CPI/FATF), domain WHOIS, IBAN validation, EU VAT/VIES, wallet screening, and x402 payment history. Returns trust score 0-100 with cluster and recommendation. |\n| `/v1/risk/score` | POST | $0.65 | Quick risk score (0-100) for entity name + country. Lightweight check without the full data source scan. |\n\n### Reputation management\n\n| Endpoint | Method | Price | Description |\n|----------|--------|-------|-------------|\n| `/v1/reputation/score` | POST | $0.65 | Reputation scoring with Bayesian trust decay. Tracks entity trust over time with confidence intervals. |\n| `/v1/reputation/history/{id}` | GET | $0.10 | Reputation history for an entity. |\n\n### Wallet services\n\n| Endpoint | Method | Price | Description |\n|----------|--------|-------|-------------|\n| `/v1/wallet/balance` | GET | $0.10 | ERC-8004 agent wallet balance — USDC balance and transaction count for AI agent wallets. |\n\n### Regulatory compliance\n\n| Endpoint | Method | Price | Description |\n|----------|--------|-------|-------------|\n| `/v1/kyb/check` | POST | $1.50 | Know Your Business verification — company registration, sanctions screening, VAT/VIES, and domain analysis in one call. |\n| `/v1/compliance/alerts` | GET | $0.10 | EU regulatory change alerts filtered by jurisdiction and severity. Covers GDPR, EU AI Act, MiCA, and AMLD6. |\n| `/v1/compliance/report/{id}` | GET | $0.50 | Compliance report for an entity. |\n| `/v1/compliance/readiness/{id}` | GET | $0.10 | Compliance readiness check for an entity. |\n\n### MCP tool paths (direct HTTP)\n\nThe 5 MCP tools are also reachable over plain HTTP at their own x402-priced paths — same\ncapabilities and prices as the Tools table above, for clients that pay per call without opening an\nMCP session.\n\n| Endpoint | Method | Price | MCP tool |\n|----------|--------|-------|----------|\n| `/v1/mcp/check-entity` | POST | $0.85 | `check_entity` |\n| `/v1/mcp/check-agent` | POST | $0.00 | `check_agent` |\n| `/v1/mcp/trust-score` | POST | $0.00 | `get_trust_score` |\n| `/v1/mcp/verify-wallet` | POST | $0.00 | `verify_wallet` |\n| `/v1/mcp/risk-score` | POST | $0.65 | `get_risk_score` |\n\n### API key tiers\n\nLimitGuard accepts two forms of payment: x402 per call, or a **paid-tier** API key whose\nsubscription prepays the calls. Paying per call needs no API key on 13 of the 18 endpoints — the\n9 data endpoints above and the 4 `/v1/keys/upgrade/*` paths. The other 5 always want a key: the\nMCP transport takes `Authorization: Bearer` on every `tools/call`, and its `/v1/mcp/*` mirrors\ntake `X-API-Key`.\n\nA base key is free and self-service: `POST /v1/keys/create` with an email address, no payment and\nno existing key needed. It identifies you and tracks your usage; it does **not** pay for calls. A\n`free`-tier key still owes x402 on every paid endpoint, on REST exactly as on MCP. The\n`monthly_limit` it reports is a ceiling on how many calls it may make, not an allowance of free\nones. A `sandbox` key is also free and returns mock data, never a real check — over MCP it owes\nx402 like any other free key, so it earns its keep only against the REST mirrors.\n\nThe endpoints below take an x402 payment to move a key onto a paid tier, which is what lifts the\nper-call charge. On a paid tier `monthly_limit` is the number of calls the subscription covers.\nThe manifest prices the upgrade call itself and says nothing about what happens at the end of a\nmonth, so confirm the renewal terms before budgeting against the figures below.\n\n| Endpoint | Method | Price | Tier | `monthly_limit` |\n|----------|--------|-------|------|-----------------|\n| `/v1/keys/upgrade/indie` | POST | $29 | Indie | 1,000 calls/mo |\n| `/v1/keys/upgrade/starter` | POST | $99 | Starter | 10,000 calls/mo |\n| `/v1/keys/upgrade/growth` | POST | $299 | Growth | 50,000 calls/mo |\n| `/v1/keys/upgrade/pro` | POST | $999 | Pro | 250,000 calls/mo |\n\nPrices and descriptions above mirror the live x402 manifest as of 2026-09-05. The manifest is the\nsource of truth — fetch it if you need the current schema for any endpoint.\n\n## Quick Start\n\n### Claude Desktop\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"limitguard\": {\n      \"type\": \"url\",\n      \"url\": \"https://api.limitguard.ai/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_LIMITGUARD_KEY\"\n      }\n    }\n  }\n}\n```\n\n### Cursor\n\nAdd to MCP settings:\n\n```json\n{\n  \"limitguard\": {\n    \"type\": \"url\",\n    \"url\": \"https://api.limitguard.ai/mcp\",\n    \"headers\": {\n      \"Authorization\": \"Bearer YOUR_LIMITGUARD_KEY\"\n    }\n  }\n}\n```\n\n### Smithery\n\n```bash\nnpx -y @smithery/cli install @limitguard/trust-intelligence\n```\n\n### Any MCP Client\n\nConnect to `https://api.limitguard.ai/mcp` using Streamable HTTP transport (POST),\nsending `Authorization: Bearer <key>` on every `tools/call`.\n\n## Discovery Endpoints\n\n| Endpoint | URL |\n|----------|-----|\n| MCP server card | [/.well-known/mcp/server-card.json](https://api.limitguard.ai/.well-known/mcp/server-card.json) |\n| MCP Tools | [/.well-known/mcp.json](https://api.limitguard.ai/.well-known/mcp.json) |\n| x402 Pricing | [/.well-known/x402.json](https://api.limitguard.ai/.well-known/x402.json) |\n| Health | [/health](https://api.limitguard.ai/health) |\n\nThe service publishes two tool cards, and they do not agree. Both list the same five\ntools, taking the same required arguments, so a `tools/call` written against either one\nworks — but the descriptions and the argument wording differ between them. The Tools\ntable above and this repository's `server.json` are generated from the **server card**,\nwhich is the one to read when the two disagree. Reconciling them is the service's to fix.\n\n## Use Cases\n\n- **KYC/KYB Automation** — AI agents verify business entities before transactions\n- **Sanctions Screening** — Check entities against OpenSanctions watchlists\n- **Agent-to-Agent Trust** — Verify counterparty agent reputation before collaboration\n- **Wallet Verification** — Check blockchain wallet risk before on-chain transactions\n- **Due Diligence** — Automated entity research with trust scoring\n\n## Security\n\n- HTTPS with TLS 1.3\n- x402 payment protocol for per-call billing (no stored payment credentials)\n- GDPR-compliant (EU-hosted, data minimization)\n- All tools are read-only (no data modification)\n- Rate limited per payment (abuse-proof)\n\n## Links\n\n- **Website:** [limitguard.ai](https://limitguard.ai)\n- **Status:** [status.limitguard.ai](https://status.limitguard.ai)\n- **MCP Registry:** [ai.limitguard.api/trust-intelligence](https://registry.modelcontextprotocol.io/v0/servers/ai.limitguard.api%2Ftrust-intelligence/versions/latest) (JSON; the registry has no HTML page per server)\n\n## License\n\nMIT\n",
  "bytes": 11471,
  "sha": "78bc61a79709e867ac20ca7b6a1db5010a6c07b92c815f9ca4aafa8d4fdf8942",
  "repo_slug": "jwconsultancyteam/limitguard-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_limitguard_api_trust_intelligence_c44e2576/readme"
}