How to Pull LinkedIn Profile Data With an MCP Server (Claude and REST)

TL;DR

• You do not scrape LinkedIn. You ask a people database, over MCP or REST, for profiles you can match by LinkedIn URL, title or company.
• It takes about 15 minutes. Counting is free. Each profile you enrich or search result you receive spends 1 LeadOcean record, so the walkthrough spends about 3.
• LeadOcean returns profile and career data. It does not return LinkedIn posts, comments or reactions. If you need post data, you need a different tool.

Prerequisites

• A LeadOcean account on the Free plan: 1,000 records for life, no card, 5 requests a second. Sign up here.
• For the REST steps: an API key exported as $LEADOCEAN_API_KEY, and curl.
• For the MCP steps: Claude Desktop, Claude Code or any client that supports remote MCP with OAuth. The server URL is https://api.leadocean.io/mcp. You sign in with OAuth and paste no key.

Step 1: Connect the MCP server

Add LeadOcean as a remote MCP server. In Claude Code:

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

Your client opens an OAuth sign-in. Approve it. The server exposes 13 tools. Seven cost nothing: leadocean_count_leads, leadocean_count_companies, leadocean_list_filters, leadocean_list_enum_values, leadocean_get_account, leadocean_get_export and leadocean_list_exports. search_leads, get_lead, find_phone, get_company, search_companies and export_leads spend records.

Step 2: Size the audience for free

Ask before you pull. A count never spends a record.

Use leadocean_count_leads: jobLevel VP, jobFunction "Sales & Business Development",
country CA. Do not fetch any people.

The tool call behind that prompt:

{
  "jobLevel": ["VP"],
  "jobFunction": ["Sales & Business Development"],
  "country": ["CA"],
  "facets": false
}

Enum values are exact strings. If a filter returns nothing, ask leadocean_list_enum_values for the right spelling before you guess.

Step 3: Pull the profiles

Now ask for a small page. This spends records, so keep the limit low while you test.

Use leadocean_search_leads with the same filters and limit 2.
Show name, title, company and LinkedIn URL.

The REST equivalent. The body is flat JSON and filters are arrays:

curl -s https://api.leadocean.io/v1/people/search \
  -H "x-api-key: $LEADOCEAN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "jobLevel": ["VP"],
    "jobFunction": ["Sales & Business Development"],
    "country": ["CA"],
    "limit": 2
  }'

Search pages with cursor, at 1 to 100 rows a page. One search pages to 10,000 rows. Narrow the filters instead of walking further.

Step 4: Enrich one LinkedIn URL

You already have a profile URL and want the record behind it. Enrich takes exactly one of linkedin_url, email, phone or person_id.

curl -s 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/jane-doe-example",
    "reveal_email": true
  }'

A person we hold nothing for returns 404 and costs nothing. Since October 2026 the response also carries career history under resume_data: past roles, educations, certifications and awards, each when held. Past employers have no company_id yet.

In Claude, say: "Use leadocean_get_lead on this LinkedIn URL and summarize the last three roles." That call costs 1 record if a profile is found and nothing if not.

Step 5: Add a phone number, only if you need it

Phones are a separate call: GET /v2/people/phone. A v2 contact call costs one record even when it finds nothing, so enrich first and ask for a phone only on the people who matter.

curl -s "https://api.leadocean.io/v2/people/phone?linkedin_url=https%3A%2F%2Fwww.linkedin.com%2Fin%2Fjane-doe-example" \
  -H "x-api-key: $LEADOCEAN_API_KEY"

The endpoint takes one of linkedin_url, person_id or contact_id as a query parameter. It returns the numbers best first, each with phone and type, or found: false.

Step 6: Export the whole list

When the count looks right, export instead of paging. Exports take up to 50,000 rows a request and 500,000 a day. Bulk CSV export is not on Free, so this step needs Solo ($97 a month) or higher.

curl -s https://api.leadocean.io/v1/exports \
  -H "x-api-key: $LEADOCEAN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "filters": {
      "jobLevel": ["VP"],
      "jobFunction": ["Sales & Business Development"],
      "country": ["CA"]
    },
    "limit": 5000
  }'

The export body nests the search filters under filters, with limit beside them. Every row costs one record.

You can also do this from app.leadocean.io: the Exports page has a filter builder, a column picker and a price preview before you download the CSV.

What you get

This is the real output of the free count in Step 2, run on 2026-10-21:

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

Read it carefully. total counts people with a verified, catch-all-valid or catch-all email, the default. totalAll is the same filters with no email condition. The call spent 0 records.

The enrich response has this outline. Response shape from the API reference, with placeholder values:

{
  "success": true,
  "data": {
    "profile_data": { "profile_full_name": "Jane Doe" },
    "contact_data": {
      "has_email": true,
      "email_status": "verified",
      "contact_current_experiences": [ { "company_name": "Acme" } ]
    },
    "resume_data": { "experiences": [], "educations": [] }
  }
}

The current role sits in contact_current_experiences[]. Past roles sit in resume_data, each when held. Fetch api.leadocean.io/openapi.json once and map the fields you need.

Troubleshooting

FAQ