How to Enrich B2B Contacts Inside Claude (LeadOcean MCP)

Claude enrichment means Claude calls a data source for you: you give it a LinkedIn URL, it returns the email, status, phone and career history that source holds. Claude has no contact data of its own. You need to attach a source, and an MCP server is the shortest route.

This guide uses the LeadOcean MCP server. It takes about 15 minutes and spends 3 records on the test.

TL;DR

• Takes about 15 minutes: 5 to connect, 5 to size a list for free, 5 to enrich three people.
• Spends 1 record per matched person. Counts, filter lookups and a person we hold nothing for cost 0.
• Past about 25 people, stop pasting prompts and run the same call from a script (Step 4).

Prerequisites

• A LeadOcean account. Start free: no card, 1,000 records, one-off.
• A Claude account that can add a custom connector. The Claude connector docs, October 2026, describe the steps.
• For Step 4 only: an API key from the app, saved as $LEADOCEAN_API_KEY, plus curl and jq.

Step 1: Connect the LeadOcean MCP server

Add https://api.leadocean.io/mcp as a custom connector and sign in with OAuth. No key is pasted.

Customize > Connectors > + Add > Add custom connector
Name: LeadOcean
URL:  https://api.leadocean.io/mcp

The server exposes 13 tools. Seven are free: leadocean_count_leads, leadocean_count_companies, leadocean_list_filters, leadocean_list_enum_values, leadocean_get_account, leadocean_get_export and leadocean_list_exports. The full click path is on the Claude setup page.

Step 2: Size the list before you spend a record

Ask Claude for a count first. It costs nothing and tells you whether the filters are worth enriching.

Using LeadOcean, count VPs in Sales & Business Development located in Canada.
Do not search for anyone. Say what the count includes.

Claude calls leadocean_count_leads with jobLevel, jobFunction and country. Filter values are exact strings, so Claude checks them with leadocean_list_enum_values when it is unsure. For a company list, leadocean_count_companies does the same job for free.

Step 3: Enrich three people in chat

Pick three LinkedIn URLs and cap the run. The cap keeps the spend visible.

Enrich these 3 people with leadocean_get_lead using reveal_email true:
https://www.linkedin.com/in/janedoe-example
https://www.linkedin.com/in/johnroe-example
https://www.linkedin.com/in/sampleperson-example
Return a table: name, title, company, email, email_status, phone.
If someone is not found, write "not found". Do not guess an address.

Each found person costs 1 record. A person we hold nothing for costs 0, the same as a REST 404. Enrichment also returns career history: past roles, education, certifications and awards. Past employers carry no company_id yet.

Read email_status before you send. LeadOcean gives no refund for bounced emails.

Step 4: Script it past 25 people

The same lookup over REST is POST /v1/people/enrich. It takes exactly one of linkedin_url, email, phone or person_id.

curl -s -X POST https://api.leadocean.io/v1/people/enrich \
  -H "x-api-key: $LEADOCEAN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"linkedin_url":"https://www.linkedin.com/in/janedoe-example","reveal_email":true}' |
  jq '{email: .data.contact_data.contact_emails[0].email,
       status: .data.contact_data.email_status,
       phone: .data.contact_data.contact_phones[0].phone}'

There is no name plus domain lookup. To start from a company, search by domain, then enrich by person_id. For a whole list, POST /v1/exports writes up to 50,000 rows a request. Bulk export is not on Free.

What you get

Step 2 returned this on 2026-10-21 (leadocean_count_leads with its default email condition, so total is the mailable audience):

{"total":5574,"totalIsExact":true,"totalAll":18800,"distinctCompanies":3873,"credits":0}

The count covers people whose best email is verified, catch_all_valid or catch_all. Without the email condition the same filters match 18,800.

Steps 3 and 4 return one record per matched person. This is the response shape from the API reference, October 2026, with placeholder values:

{
  "success": true,
  "data": {
    "profile_data": { "...": "name, title, company" },
    "contact_data": {
      "has_email": true,
      "has_phone": true,
      "email_status": "verified",
      "contact_emails": [{ "email": "jane.doe@acme.com", "type": "work", "status": "verified" }],
      "contact_phones": [{ "phone": "+14155550133", "type": "mobile" }]
    }
  }
}

Without reveal_email, the address arrays are absent. has_email and has_phone still say whether a value exists.

Troubleshooting

FAQ