Skip to main content
This guide walks you through connecting the peeps MCP server to your AI assistant. By the end, you’ll have a working setup that lets your AI look up people, contacts, and organizations from your peeps workspace — all through natural language.

​
Prerequisites

Before you begin, make sure you have:

​
Setup

1

Get your API key

Log in to app.peeps.ai and navigate to Settings → API Keys. Click Create new key, give it a descriptive name (for example, claude-desktop), and copy the generated key.
Your API key is shown only once at creation time. Store it somewhere safe — if you lose it, you’ll need to generate a new one.
2

Install the MCP server

The peeps MCP server is published as an npm package. The quickest way to run it is with npx, which requires no global installation:
Alternatively, install it globally so it’s always available on your PATH:
3

Configure your MCP client

Add the peeps server to your MCP client’s configuration file. Below is the configuration for Claude Desktop — open your claude_desktop_config.json file and add the peeps entry under mcpServers:
Replace your-api-key-here with the key you copied in step 1. Save the file and restart Claude Desktop to apply the change.
The config file location depends on your OS. On macOS it lives at ~/Library/Application Support/Claude/claude_desktop_config.json; on Windows at %APPDATA%\Claude\claude_desktop_config.json.
4

Ask your AI about people

Open a new conversation in your AI assistant and try one of these prompts to confirm everything is working:
  • “Find everyone named Sarah at Acme Corp.”
  • “Look up John Smith’s contact details.”
  • “Show me all contacts at Globex Corporation.”
  • “What organizations do we have in peeps?”
Your AI will call the peeps MCP server behind the scenes and return real data from your workspace.
Want to see everything your AI can do with peeps? Check out the Tools Reference for a full list of available operations, including search filters, field descriptions, and example responses.