Skip to main content

​
Overview

The Suki Developer Documentation is available as an MCP server (Model Context Protocol) that you can connect directly to your AI code editor like (Cursor, VS Code) while working on your local development environment. This connection allows the LLM in your editor to query our documentation and use Suki’s API reference during its response generation. For example, if you ask a coding question, the LLM determines that Suki’s API documentation is relevant. It will then search our reference and include the necessary information in the response, without you explicitly having to ask about our documentation.
The Suki Developer Documentation MCP server includes the search tool by default, which allows the LLM to query information from the documentation.

​
Key Benefits

The MCP integration provides the following benefits:

Accelerate your development

Use the documentation as an MCP service in your AI code editor to assist your coding and integration tasks.

Improve your LLM's responses

Retrieve information from the documentation in your AI code editor to improve the accuracy of the responses.

Reduce the need for manual research

Reduce the need for manual research and documentation lookup.

Improve your productivity

Improve your productivity as you can focus on the code and let the LLM handle the documentation lookup and response generation.

Reduce LLM hallucinations

Reduce LLM hallucinations and improve the accuracy of the responses by using the documentation as an MCP service.

​
How To Setup MCP Integration?

To integrate our developer documentation as an MCP service into your AI code editor, follow the steps for your specific editor. You will use the following URL as the custom connector endpoint: 
https://developer.suki.ai/mcp
You will use this URL to install our MCP server as a custom connector in the following code editors.
  • Cursor
  • Claude
  • Claude Code
  • VS Code

Open MCP settings in Cursor

  1. Use (Command + Shift + P on Mac) or (Ctrl + Shift + P on Windows) to open the command palette.
  2. Search for Open MCP settings to open the MCP settings.
  3. Select Add custom MCP. This will open the mcp.json file.
  4. In mcp.json, configure your server by adding the following JSON object:
{
  "servers": [
    {
      "url": "https://developer.suki.ai/mcp"
    }
  ]
}
We recommend using the MCP server URL in Cursor .