Introduction
What is MCP?
The Model Context Protocol (MCP) is an open standard for connecting AI assistants to external data and tools. The Org provides an MCP server so you can use Claude, Cursor, and other MCP-compatible clients to query org charts, find managers, search positions, and check your API usage in natural language.
What you can do
Once connected, your AI assistant can call these tools on your behalf:
| Tool | Description | Credits |
|---|---|---|
| get_org_chart | Fetch the full org chart for a company (by domain or LinkedIn URL) | 10 per request |
| get_manager | Find the manager of a person (by work email or LinkedIn URL) | 1 per find |
| get_usage | Check your remaining API credits and usage | Free |
| find_positions | Search positions with filters (company, department, job titles, etc.) | 1 per row returned |
Credits are deducted from the same balance as your API usage.
Integration with AI assistants
The MCP server works with any client that supports MCP over HTTP, including:
- Claude Desktop – via mcp-remote and your config file
- Cursor – built-in MCP support in Settings
Authentication uses your existing API key . No separate MCP sign-up is required.
For setup, see Get started. For endpoint details, protocol, and examples, see the MCP API reference.
Last updated on