> ## Documentation Index
> Fetch the complete documentation index at: https://docs.peepsai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Install the peeps MCP server via npx, npm, or remote

> Get the peeps MCP server running via npx, global npm install, or the hosted remote server. Includes prerequisites, steps, and upgrade instructions.

The peeps MCP server is distributed as an npm package (`@peeps-ai/mcp`) and can be run with `npx`, installed globally, or skipped entirely in favor of the peeps-hosted remote server. Pick the option that best fits your environment — all three expose the same tools to your AI assistant.

## Prerequisites

Before you install, make sure you have the following:

* **Node.js 18 or later** — required for the `npx` and global install options. Run `node --version` to check.
* **A peeps account** — sign up at [app.peeps.ai](https://app.peeps.ai) if you don't have one.
* **A peeps API key** — find yours in the [peeps dashboard settings](https://app.peeps.ai/settings/api-keys).

<Note>
  You can grab your API key from **Settings → API Keys** inside the [peeps dashboard](https://app.peeps.ai/settings/api-keys). Keep it somewhere safe — you'll need it in every installation option below.
</Note>

## Installation options

<Steps>
  <Step title="Choose your installation method">
    Pick one of the three options below based on your environment. Most users should start with **Option 1 (npx)**.
  </Step>

  <Step title="Set your API key and run the server">
    <CodeGroup>
      ```bash Option 1: npx (recommended) theme={null}
      # Run directly — no installation required.
      # npx downloads and executes the latest version automatically.
      PEEPS_API_KEY=your-api-key npx -y @peeps-ai/mcp
      ```

      ```bash Option 2: Global install theme={null}
      # Install once, then run the peeps-mcp command from anywhere.
      npm install -g @peeps-ai/mcp

      # After installing, start the server:
      PEEPS_API_KEY=your-api-key peeps-mcp
      ```

      ```bash Option 3: Remote server (no install) theme={null}
      # No local installation needed.
      # Point your MCP client at the hosted SSE endpoint:
      #
      #   https://mcp.peeps.ai/sse
      #
      # Pass your API key as a Bearer token in the Authorization header.
      # See your client's documentation for how to configure headers.
      ```
    </CodeGroup>
  </Step>

  <Step title="Verify the connection">
    Once the server is running (or your client is pointed at the remote URL), ask your AI assistant a question that requires contact data — for example: *"Search for engineers at Acme Corp."* A successful response means the MCP server is connected and authenticated.
  </Step>
</Steps>

## Option details

### Option 1: Run with npx (recommended)

`npx` runs the MCP server without a permanent installation. Your MCP client (Claude Desktop, Cursor, etc.) typically handles launching the process for you — you just supply the command and your API key in the client's config file.

```bash theme={null}
PEEPS_API_KEY=your-api-key npx -y @peeps-ai/mcp
```

The `-y` flag skips the confirmation prompt so the server starts immediately. This is the method used in the [Claude Desktop and Cursor configuration examples](/mcp/configuration).

### Option 2: Install globally

If you prefer a persistent, version-pinned installation, install the package globally with npm:

```bash theme={null}
npm install -g @peeps-ai/mcp
```

Then start the server with:

```bash theme={null}
PEEPS_API_KEY=your-api-key peeps-mcp
```

To upgrade to a newer version later:

```bash theme={null}
npm update -g @peeps-ai/mcp
```

### Option 3: Use the remote server

Connect directly to the peeps-hosted MCP server without installing anything locally. This option is ideal for cloud-hosted agents and serverless environments.

```
https://mcp.peeps.ai/sse
```

Authenticate by passing your API key as a Bearer token in the `Authorization` header:

```http theme={null}
Authorization: Bearer your-api-key-here
```

Refer to your MCP client's documentation for how to configure custom headers on an SSE transport connection. See the [configuration guide](/mcp/configuration) for a generic JSON example.

<Warning>
  Never hard-code your API key in a script or config file that gets committed to version control. Use environment variables or a secrets manager instead. See the [configuration guide](/mcp/configuration) for safe patterns.
</Warning>