Limitguard Lead Verification

Limitguard MCP Server

Lead validation over the Model Context Protocol: check the company behind each lead against the KVK (Netherlands) or KBO (Belgium) register, EU VAT (VIES), sanctions lists and its email domain, in one tool call. Company, sanctions and wallet checks for developers and AI agents sit beside it.

Server URL: https://api.limitguard.ai/mcp Transport: Streamable HTTP (POST) Auth: API key (Bearer), plus an x402 micropayment per call on the free and sandbox tiers

What it is: Limitguard is a lead validation service for lead generation agencies, B2B marketing and sales teams: it checks the company behind each lead against official business registers (full coverage in the Netherlands and Belgium), EU VAT and sanctions lists, with website age in the company check, and returns proceed, review or block with the source on every line. Developers and AI agents can use its HTTP API, MCP server and A2A service, hosted in the EU.

Start here: On MCP a paid tool takes an x402 payment per call, or debits prepaid credit (a paid key, or a funded workspace); verify_wallet, sanctions_preview and get_trust_score are free; the free sandbox key returns mock data on the REST API only, not on MCP. Lead Verify $0.27 per lead and agent check $0.75 per wallet; $0.11-1.85 per call; entity and risk checks $0.88-1.05 fresh ($1.50 KYB), $0.11 cached ($0.25 KYB) when available.

Tools

tools/list is public: connect and read it without any credential. These are the names it returns, and the names tools/call accepts:

Pricing

A paid tool call is debited from your API key's prepaid balance, or paid per call with an x402 micropayment (USDC on Base or Solana). The tools with their own /v1/mcp/* path are priced below; the other tools are priced at the REST endpoint they call, in Full x402 API.

Authentication

Two things gate a tools/call, in this order:

1. An API key, as Authorization: Bearer <key>. Without one every call comes back Authentication required. Provide API key via Authorization: Bearer <lg_live_...> header. Get a free one (no payment, no card):

   curl -X POST https://api.limitguard.ai/v1/keys/create \
     -H "Content-Type: application/json" \
     -d '{"email": "you@example.com"}'
   

   That returns a free-tier key, which is the key the Quick Start configs below expect. Asking for "tier": "sandbox" instead returns a key that answers with mock data; see the next point before you use one here.

2. Payment, on the free and sandbox tiers only. Send the x402 proof as PAYMENT-SIGNATURE (x402 v2) or X-PAYMENT (v1), alongside the Bearer key. A key with a prepaid balance (indie and up) is debited per call instead and needs no per-call payment. API keys have no subscription; see API keys and prepaid balance.

   A sandbox key does not lift the payment requirement on this transport: it owes x402 per call exactly as a free key does, and it answers with mock data rather than a real check. Paying for one over MCP spends real USDC on a mock answer. Where a sandbox key is worth having is the REST mirrors under /v1/mcp/* (sent as X-API-Key, not Bearer), which serve the mock response before the payment check: a way to exercise the request and response shapes, not a cheap source of real checks.

Full x402 API (direct HTTP)

The tools above are what the MCP server exposes over the Model Context Protocol. Clients that integrate directly over HTTP, instead of through an MCP client, can reach every x402-priced endpoint on https://api.limitguard.ai: the REST endpoints below, plus the MCP tools' own /v1/mcp/* paths. All of them are published in /.well-known/x402.json; /.well-known/mcp.json lists only the tools above.

Most of the REST endpoints are capabilities the MCP tools do not expose, but two run the same engine over plain HTTP: /v1/entity/check behind check_entity (the MCP tool takes the entity name, country, KVK number and domain only, so no IBAN or VAT), and /v1/risk/score behind get_risk_score, at the same price.

Payment works the same way throughout: USDC on Base or Solana, pay-per-call. The data endpoints below need no API key at all. The /v1/keys/upgrade/* endpoints also take payment without one, but they act on an API key you already hold; see API keys and prepaid balance.

Lead and company checks

Reputation management

Wallet services

Regulatory compliance

MCP tool paths (direct HTTP)

The MCP tools that mirror a REST check are also reachable over plain HTTP at their own x402-priced /v1/mcp/* paths, with the same capabilities and prices as the Tools table above, for clients that pay per call without opening an MCP session. The other tools call one of the REST endpoints above directly.

API keys and prepaid balance

Limitguard accepts two forms of payment: x402 per call, or an API key with a prepaid balance that each priced call is debited from. API keys and x402 have no subscription (the Limitguard dashboard also has optional monthly plans, paid in euros). Paying per call needs no API key on the data endpoints above or the /v1/keys/upgrade/* paths. The MCP transport always wants one: it takes Authorization: Bearer on every tools/call, and its /v1/mcp/* mirrors take X-API-Key.

A base key is free and self-service: POST /v1/keys/create with an email address, no payment and no existing key needed. It identifies you and tracks your usage; it does not pay for calls. A free-tier key holds no balance and still owes x402 on every paid endpoint, on REST exactly as on MCP. The monthly_limit it reports is a ceiling on how many calls it may make, not an allowance of free ones. A sandbox key is also free and returns mock data, never a real check. Over MCP it owes x402 like any other free key, so it earns its keep only against the REST mirrors.

The endpoints below take an x402 payment, credit the same amount 1:1 to the prepaid balance of a key you already hold, and set its tier label. Each priced call is then debited from that balance at the prices above, with no per-call x402 payment. When the balance is too low for a call, that call answers 402 with an x402 quote and the top-up path, and POST /v1/keys/topup/{usd} adds any whole-dollar amount from $5. On every tier monthly_limit is an abuse limit, not an allowance of included calls.

Prices and descriptions above are generated from the service and were last checked against the live x402 manifest on 2026-10-06. The manifest is the source of truth: fetch it if you need the current schema for any endpoint.

Quick Start

Claude (Desktop and claude.ai)

This is a remote server, so it is added as a custom connector, not in claude_desktop_config.json (that file is for local servers only):

1. Open Customize > Connectors, then + Add > Add custom connector. On a Team or Enterprise plan an owner adds it under Organization settings > Connectors.
2. URL: https://api.limitguard.ai/mcp
3. Under Request headers, add Authorization with the value Bearer YOUR_LIMITGUARD_KEY.

Cursor

Add to MCP settings:

{
  "limitguard": {
    "type": "url",
    "url": "https://api.limitguard.ai/mcp",
    "headers": {
      "Authorization": "Bearer YOUR_LIMITGUARD_KEY"
    }
  }
}

Smithery

npx -y @smithery/cli install team-mehs/limitguard

Any MCP Client

Connect to https://api.limitguard.ai/mcp using Streamable HTTP transport (POST), sending Authorization: Bearer <key> on every tools/call.

Discovery Endpoints

The service publishes two tool cards, and they do not fully agree. Both list the same tools, taking the same required arguments, so a tools/call written against either one works, but the descriptions and the argument wording differ between them. The Tools table above and this repository's server.json are generated from the server card, which is the one to read when the two disagree. Reconciling them is the service's to fix.

Use Cases

• Lead validation: check the company behind each lead (KVK or KBO register, EU VAT via VIES, sanctions lists and email domain) before it reaches a client, and get a verdict, a 0-100 lead score and flags (verify_lead).
• Company checks: developers and AI agents verify a business entity before a deal or a payment (check_entity, get_risk_score), or build a per-entity report with every source's status (get_compliance_report).
• Sanctions screening: screen a company or person name against the OFAC, EU and UN lists (sanctions_preview, sanctions_screen).
• Agent-to-agent checks: check a counterparty agent's wallet and ERC-8004 identity before working with it (check_agent_wallet).
• Wallet screening: screen a wallet address before an on-chain payment (verify_wallet).

Security

• HTTPS with TLS 1.3
• x402 payment protocol for per-call billing (no stored payment credentials)
• Hosted in the EU (API and dashboard in the EU, database in Ireland); data minimisation
• All tools are read-only (no data modification)
• Rate limited per payment (abuse-proof)

Links

• Website: limitguard.ai
• Status: status.limitguard.ai
• MCP Registry: ai.limitguard.api/trust-intelligence (JSON; the registry has no HTML page per server)

License

MIT