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

# Connect AI Assistants via Parallel AI MCP Integration

> Parallel AI's MCP server lets Claude Desktop, Cursor, Windsurf, and other AI tools access your agents, sequences, documents, and more.

## What is MCP?

Model Context Protocol (MCP) is an open standard for connecting AI assistants to external tools and data sources. With Parallel AI's MCP server, your AI assistant can:

* Browse and manage your AI agents
* Create and monitor outreach sequences
* Search your knowledge base documents
* Generate AI content, images, audio, and video
* Execute browser automation tasks
* Access every platform feature via natural language

## MCP Server URL

```
https://api.parallellabs.app/api/v0/mcp
```

<Note>
  This server implements MCP Streamable HTTP Transport (JSON-RPC 2.0). It is
  compatible with `mcp-remote` and other standard MCP clients.
</Note>

## Available Tools

| Tool                          | Description                                                 |
| ----------------------------- | ----------------------------------------------------------- |
| `platform_list_capabilities`  | Browse available API endpoints by category                  |
| `platform_get_action_details` | Get the full spec for an endpoint including required params |
| `platform_execute_action`     | Execute any API endpoint with automatic authentication      |

## Connecting Claude Desktop

<Steps>
  <Step title="Open your Claude Desktop config file">
    Locate the configuration file for your operating system:

    * **macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json`
    * **Windows:** `%APPDATA%\Claude\claude_desktop_config.json`
  </Step>

  <Step title="Add the MCP server">
    Paste the following into your config file, replacing `your_api_key_here` with your actual API key:

    ```json claude_desktop_config.json theme={null}
    {
      "mcpServers": {
        "parallel-ai": {
          "command": "npx",
          "args": ["-y", "mcp-remote", "https://api.parallellabs.app/api/v0/mcp"],
          "env": {
            "API_KEY": "your_api_key_here"
          }
        }
      }
    }
    ```
  </Step>

  <Step title="Restart Claude Desktop">
    Fully quit and relaunch Claude Desktop so it picks up the new configuration.
  </Step>

  <Step title="Test the connection">
    Ask Claude something like:

    * *"List my AI agents"*
    * *"Create a new email sequence for cold outreach"*

    Claude will automatically use the Parallel AI tools to fulfill your request.
  </Step>
</Steps>

## Connecting Cursor / Windsurf

<Steps>
  <Step title="Open the MCP settings">
    Navigate to **Settings → MCP** inside Cursor or Windsurf.
  </Step>

  <Step title="Add a new MCP server">
    Fill in the following details:

    * **URL:** `https://api.parallellabs.app/api/v0/mcp`
    * **Authentication:** Bearer token using your Parallel AI API key
  </Step>

  <Step title="Confirm the tools are available">
    The Parallel AI platform tools will appear in your AI assistant's tool list. You can now reference them directly in your prompts.
  </Step>
</Steps>

## Generic mcp-remote Connection

If you're using any MCP client that supports `mcp-remote`, connect with a single command:

```bash theme={null}
npx mcp-remote https://api.parallellabs.app/api/v0/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"
```

## Authentication for MCP

MCP authentication follows the same pattern as the REST API.

**Company API Key:**

```
Authorization: Bearer YOUR_COMPANY_API_KEY
```

**Personal Access Key:**

```
Authorization: Bearer pak_your_key
X-Company-ID: your_company_id
```

<Tip>
  You can find your API keys on the **Integrations** page (Company API Keys) or
  your **Profile** page (Personal Access Keys) in the Parallel AI dashboard.
</Tip>

## Example MCP Interactions

The three tools work together to let your AI assistant discover and execute any platform action.

<CodeGroup>
  ```json platform_list_capabilities theme={null}
  {
    "tool": "platform_list_capabilities",
    "input": {
      "category": "Sequences"
    }
  }
  ```

  ```json platform_get_action_details theme={null}
  {
    "tool": "platform_get_action_details",
    "input": {
      "operationId": "post_sequences.create_sequence"
    }
  }
  ```

  ```json platform_execute_action theme={null}
  {
    "tool": "platform_execute_action",
    "input": {
      "operationId": "get_agents.list_agents",
      "parameters": {}
    }
  }
  ```
</CodeGroup>

<Note>
  For the full MCP API reference, including all available operation IDs and
  response schemas, see the [MCP Overview](/api-reference/introduction).
</Note>