Integration

Greip integration

Greip is a fraud prevention and data lookup API. Geolocate any IP address (or up to a short list at once) with optional security, timezone, currency and location modules; score an IP address, email address or phone number for fraud risk; validate an IBAN; look up a card BIN, an autonomous system number, a domain or a country; detect profanity in text; score a payment transaction; and delete the data Greip stores about one of your users. Every result carries a risk level or validity flag a workflow can branch on, and errors come back with success false plus a code, type and description. The routes that only describe the caller (its own IP and geolocation), JSONP callbacks and the XML, CSV and newline output formats are not included. Each endpoint needs a Standard or Premium plan (a 3-day trial exists), and mode=test returns fake data without using quota. Authentication is a Greip API key sent as a Bearer token in the Authorization header.

Connect Greip How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Greip.Built from the 13 Greip tools below, on the connection you add once.

What you can do with Greip

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Ip, 2 operations

lookup_ipLookup ipGETLooks up one IPv4 or IPv6 address: continent, country, region, city, postal code, coordinates and its autonomous system, plus the optional modules named in params (security, timezone, currency, location). Standard plan and above.
score_ipScore ipGETScores the fraud risk of an IP address: a score, a risk level (low, medium, high) and a recommendation (accept, review, reject), with the triggered rules and security signals (VPN or proxy, Tor, bot, hosting, blacklist).

Asn, 1 operation

lookup_asnLookup asnGETLooks up an autonomous system number: its name, organisation, country, contact phone and email, domain, registry, status, creation date, type and the IPv4 and IPv6 prefixes it announces. Premium plan and above.

Bin, 1 operation

lookup_card_binLookup card binGETIdentifies a payment card from its BIN (first 6 or more digits): validity, scheme (Visa, Mastercard...), debit or credit, prepaid or commercial, brand, issuing bank and country. Standard plan and above.

Bulk, 1 operation

lookup_ips_bulkLookup ips bulkGETLooks up several IP addresses in one call and returns each one's ip and geo data (plus the modules named in params), keyed by address. Invalid and duplicate entries are skipped. Standard plan and above.

Country, 1 operation

get_countryGet countryGETReturns facts about a country from its two-letter code: continent, capital, population, dialing code, EU membership, neighbours and TLD, plus language, currency and flag when requested in params. Standard plan and above.

Domain, 1 operation

lookup_domainLookup domainGETChecks a domain name for risk: dangerous, disposable or forwarding flags, SPF, DMARC, DKIM, MX and BIMI records, creation date and whether it is new. A domain not yet known returns null values while Greip collects it (about 24 hours). Standard plan.

Email, 1 operation

score_emailScore emailGETValidates and scores an email address beyond syntax: domain validity and DNS records, disposable, free, role-based or educational address, blacklist, a risk level and a recommendation (accept, review, reject) with reasons. Premium plan.

Iban, 1 operation

validate_ibanValidate ibanGETValidates an IBAN and returns is_valid, the number in machine, human and obfuscated formats, the country (currency, SEPA and EU membership, central bank) and the bank when known. Premium plan and above.

Payment, 1 operation

score_paymentScore paymentPOSTScores a payment, deposit or withdrawal for fraud from the transaction, customer, shipping, billing and card details you send: a risk score (0 to 100), risk level, recommendation, triggered rules and velocity counts. Premium plan.

Phone, 1 operation

score_phoneScore phoneGETValidates and scores a phone number for a given country: validity, carrier, disposable or blacklisted number, a risk level and a recommendation (accept, review, reject) with reasons. Premium plan and above.

Text, 1 operation

detect_profanityDetect profanityPOSTScreens a text for profanity and offensive language before it is published, and returns a risk level (low, medium, high) and a recommendation (accept, review, reject). A clean text returns low. Standard plan and above.

User, 1 operation

delete_user_dataDelete user dataDELETEPermanently deletes everything Greip stores about one of your end users (transactions, IPs, emails, phones, IBANs, screened texts) for a data-protection request. Irreversible; at most 3 deletions per API key per 24 hours.

Use Greip from Claude Code, Cursor or Codex

Connect Greip in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Greip operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Greip

Create your workspace
Sign up free. Nothing to install.
Connect Greip once
Add your Greip connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.