The Model Context Protocol (MCP) is a standard for connecting Large Language Models (LLMs) to platforms like Unipile. Once connected, your AI assistants can interact with your Unipile accounts on your behalf.

Installation

1. Be aware of security concerns

The MCP can be used simply to help your agent understand the Unipile API design and explore available endpoints.

However, it can also be configured with your Unipile API Key to allow the agent to perform Account Methods on your behalf.

❗️

Unipile API keys currently provide full access to all connected accounts and do not support permission scoping. This means that any agent configured with your API key will be able to read data and perform actions across all accounts connected to your Application.

For this reason, only use this configuration in environments you trust, and never expose your API key to untrusted agents or publicly accessible systems.

2. Setup your client

Choose your MCP Client then follow the instructions

{
  "mcpServers": {
    "unipile": {
      "url": "https://developer.unipile.com/mcp?branch=v2.0",
      "headers": {
        "X-API-KEY": "your-api-key",
      }		
    }
  }
}

Next Step

Once configured, you can test your MCP server connection:

1. Open your AI editor (Cursor, Windsurf, etc.)
2. Start a new chat with the AI assistant
3. Ask about Unipile or Ask to perform tasks on accounts - try questions like:
   • "How do I [common use case]?"
   • "Show me an example of [API functionality]"
   • "Create a [integration type] using Unipile"
   • "Send a message to [xxxx] using account acc_1234521321"
   • "List all emails on the [[email protected]] inbox"

The AI should now have access to your Unipile account data and API Reference through the MCP server.

Available tools

• list-specs - Lists all API specs available in the project, with their titles
• list-endpoints - Returns all API paths and HTTP methods with their summaries
• get-endpoint - Returns full detail on a specific endpoint: description, parameters, security
• get-request-body - Returns the request body schema for an endpoint
• get-response-schema - Returns the response schema for a specific endpoint and status code
• list-security-schemes - Lists all authentication methods defined in your API spec
• search-specs - Case-insensitive search across all paths, operations, and schemas
• execute-request - Makes a live API call and returns the response. Requires auth headers to be forwarded
• get-code-snippet - Generates a working code snippet for any endpoint in any programming language