Xverum — MCP Server

Find and enrich people from 750M professional profiles, with Next Move Signal job-change scores. Search by role, seniority, skills, industry, and location in plain English. Pull profiles with description, work history, education, and seniority, then see who's likely to change jobs next with Next Move Signal. Built for AI products and agents: sourcing candidates, building lead lists, and mapping markets and accounts.

This is a hosted, remote MCP server — there is nothing to install or run. Point your client at the endpoint below and sign in with OAuth.

Is there an MCP server for finding people?

Yes. The Xverum MCP lets your AI assistant find and enrich the right people from a global professional-profiles dataset — no scraping, no browser tabs. Ask in plain language ("find senior data engineers in Amsterdam" or "VPs of sales at Series A SaaS companies") and it returns ranked profiles; ask about one and it pulls the full background. It's built for two jobs: sourcing job candidates by role, skills, and location, and building sales lead lists of decision-makers. Connect it to Claude or any MCP-compatible assistant in one command.

Related MCP server: abm.dev MCP server

Prerequisites

Sign up at Ask Xverum.

Connect your client

claude mcp add --transport http xverum https://mcp.xverum.com/mcp

Verify with /mcp — you should see xverum with three tools.

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "xverum": {
      "type": "http",
      "url": "https://mcp.xverum.com/mcp"
    }
  }
}

Add to .vscode/mcp.json:

{
  "servers": {
    "xverum": {
      "type": "http",
      "url": "https://mcp.xverum.com/mcp"
    }
  }
}

Most clients take a JSON config of this shape:

{
  "mcpServers": {
    "xverum": {
      "type": "http",
      "url": "https://mcp.xverum.com/mcp"
    }
  }
}

Consult your client's docs for where that file lives.

Also in the MCP Registry as com.xverum/mcp, so many agents can add it by name.

Authentication. The server uses OAuth — on first connection your client opens a browser window to sign in. No API keys to paste. See docs/authentication.md.

Tools

Full reference: docs/tools.md.

Examples

Example 1: Search people (search_people_xverum)

Senior Python developers with Kubernetes in Seattle

Example 2: Enrich a profile (enrich_person_xverum)

Get profile id 401241903

Example 3: Predict job changes (predict_job_change_xverum)

Use predict_job_change_xverum for profile ID 271961733.

Credits

1 credit per search result · 4 credits per full profile · 10 credits per job-change score. Each response reports credits_used and credits_remaining. See plans and pricing

Docs

• Quickstart — connect and run your first search.

• Tools — parameters, return shapes, and worked examples.

• Authentication — OAuth sign-in and what we store.

• Troubleshooting — error codes and what to do about them.

• Versioning — versioning scheme and deprecation policy.

Privacy & security

• Authentication is handled via OAuth — no API keys are stored or transmitted in config files.

• The server exposes exactly the three tools listed above. It cannot write, delete, or take any action on your behalf.

• Profile data comes from Xverum's licensed professional-profiles dataset.

Links

• Ask Xverum — website

• MCP Registry — com.xverum/mcp

Support

Questions or issues: open an issue on this repo, or contact us via agentic.support@xverum.com.