Enrich Person with MCP

Give Claude or Cursor a LinkedIn URL, work email, phone or person_id and the agent calls get_lead for you. One URL, OAuth sign-in, 1 record per found person.

This page is about setup and prompts. For the REST endpoint and the full schema, see Enrich Person. Other clients are on the MCP hub.

Connect the server

The server is https://api.leadocean.io/mcp. It signs in with OAuth 2.1, so there is no key to paste. Create a free account first.

Claude Code. The command format is from the Claude Code MCP docs, September 2026:

claude mcp add --transport http leadocean https://api.leadocean.io/mcp
claude mcp login leadocean

Cursor. Add a remote server to mcp.json, in the url form shown in the Cursor MCP docs, September 2026:

{
  "mcpServers": {
    "leadocean": {
      "url": "https://api.leadocean.io/mcp"
    }
  }
}

Cursor starts the sign-in the first time the server is used. In the Claude app, add the URL under Settings, Connectors. Other clients are in the LeadOcean MCP docs.

The tool

The tool is get_lead. The server lists it as leadocean_get_lead. It costs 1 record per found person, with or without reveal_email. The REST twin is POST /v1/people/enrich.

Send exactly one identifier. Two is a 400. There is no name plus company lookup, so the agent searches first and then enriches by person_id.

Prompts that work

Put the record limit in the prompt. "Stop after 25 records" is enough for the agent to hold a batch. Ask it to check has_email and has_phone on search rows first, since a row with both false has nothing to return.

What the agent gets back

The result is one leadocean.person.v1 object plus a meta block. Field groups are from the enrich docs, September 2026. Values below are placeholders.

{
  "person": {
    "profile_data": {
      "profile_full_name": "Jane Doe",
      "profile_headline": "Title at Company",
      "profile_url": "https://www.linkedin.com/in/jane-doe"
    },
    "contact_data": {
      "has_email": true,
      "email_status": "verified",
      "email_type": "work",
      "contact_emails": [
        { "email": "jane@example.com", "type": "work", "status": "verified", "verified_batch_date": "YYYY-MM-DD" }
      ],
      "contact_phones": [{ "phone": "+1 ...", "type": "mobile" }],
      "contact_current_experiences": [
        { "company_name": "Company", "company_domain": "example.com", "job_title": "Title" }
      ]
    },
    "resume_data": {}
  },
  "meta": { "source": "...", "key_hash": "...", "schema": "leadocean.person.v1" }
}

Emails and phones appear only with reveal_email true. Unknown values are null, never guessed. Over MCP, resume_data is empty today, per the server's own tool description, so do not ask the agent for career history.

Read email_type and email_status before sending. work is the current employer, work_other is usually an old one. Send to verified or catch_all_valid. There is no credit-back for bounces.

Free checks first

count_leads, list_enum_values and get_account spend no records. Run them before any paid call.

We ran count_leads with jobLevel: ["VP"], jobFunction: ["Sales & Business Development"] and country: ["US"] on 2026-10-01. It returned total: 115336, totalIsExact: true, credits: 0. That counts mailable people (verified, catch_all_valid or catch_all), not everyone we hold. Size the list first, then enrich only the people you will contact.

Troubleshooting

FAQ