Skip to main content

Documentation Index

Fetch the complete documentation index at: https://developer.suki.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

The Suki Developer Documentation is available as an MCP server (Model Context Protocol). Connect it directly to your AI code editor (Cursor, VS Code) while working in your local development environment. This connection lets the LLM in your editor search the Suki knowledge base to find code samples, API references, and guides. 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.

​
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.

​
MCP server tools

When you connect Suki’s developer documentation MCP server, it provides two tools that your AI applications can use:
  1. Search: Searches across our documentation to find relevant content, returning snippets with titles and links. Use this when you need to discover information or find pages matching a query.
  2. Get page: Retrieves the full content of a specific documentation page by its path. Use this when you already know the page path, such as from search results, and need the complete content rather than a snippet.
AI applications such as Cursor and Claude can determine when to use each tool based on the context of the conversation. For example, your AI application might first search our documentation to find relevant pages, then use the get page tool to retrieve the full content of the most relevant result.

​
Search parameters

The above MCP search tools support optional parameters that your AI applications can use to control and refine search results.
Your AI applications automatically determine when to apply these parameters based on the context of your query. For example, if you ask about a specific API version, the AI application may automatically apply the appropriate filter to provide more relevant results.

​
Get page parameters

The get page tool accepts one required parameter:
​
page
string
required
The page path to retrieve, such as ‘api-reference/create-session’. Use page paths returned from search results.

​
How to set up 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 the above URL to connect to our MCP server as a custom connector in the following code editors.

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 .
Last modified on April 21, 2026