Documentation MCP Integration

The Suki developer documentation is available as an MCP server (Model Context Protocol). Connect it to your AI code editor (Cursor, VS Code, Claude) while you work 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 the contextual menu, copy options, and one-click AI integrations on every page, refer to AI-optimized documentation.

Key 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 manual research

Reduce the need for manual research and documentation lookup.

Reduce LLM hallucinations

Ground responses in current documentation instead of invented endpoints or SDK patterns.

The documentation MCP server provides search and get page tools only. It does not execute Suki API calls on your behalf.

MCP server URL

Use the following URL as the custom connector endpoint:

https://developer.suki.ai/mcp

You can copy this URL from the Documentation MCP dropdown in the top navigation bar, from Copy MCP server URL in the contextual menu on any page, or from the configuration snippets below. The screenshot below shows the Documentation MCP dropdown in the top navigation bar:

Documentation MCP dropdown in the top navigation bar with copy snippets for MCP endpoint, Cursor mcp.json, and Claude Code CLI

The panel includes copy-ready snippets for the MCP endpoint, Cursor (mcp.json), Claude Code, VS Code (.vscode/mcp.json), and Claude (custom connector). Select the copy button next to each snippet to paste it into your editor or terminal.

MCP server tools

When you connect the Suki developer documentation MCP server, it provides two tools:

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.
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 search tool supports optional parameters that your AI applications can use to control and refine search results.

Hide Search parameters

pageSize

number

Number of results to return, between 1 and 50. Defaults to 10.

scoreThreshold

number

Minimum relevance score between 0 and 1. Only returns results at or above this threshold. Use this to filter out low-relevance matches.

version

string

Filter results to a specific documentation version. For example, v0.7. Only returns content tagged with the specified version or content available across all versions.

language

string

Filter results to a specific language code. For example, en, zh, or es. Only returns content in the specified language or content available across all languages.

Get page parameters

The get page tool accepts one required parameter:

page

string

required

The page path to retrieve, such as documentation/webhook/quickstart. Use page paths returned from search results.

How to set up MCP integration

Cursor
VS Code
Claude
Claude Code

Open MCP settings in Cursor

Use Command + Shift + P on Mac or Ctrl + Shift + P on Windows to open the command palette.
Search for Open MCP settings and select Add custom MCP. This opens mcp.json.
Add the following configuration:

{
  "servers": [
    {
      "url": "https://developer.suki.ai/mcp"
    }
  ]
}

Or select Connect to Cursor from the contextual menu on any documentation page.

Configure the MCP server in VS Code

Create a .vscode/mcp.json file in your project root.
Add the following configuration:

{
  "servers": {
    "suki-docs": {
      "type": "http",
      "url": "https://developer.suki.ai/mcp"
    }
  }
}

Add a custom connector in Claude

Navigate to the Connectors page in Claude settings.
Select Add custom connector.
Set the name to Suki Developer Documentation MCP server and the URL to https://developer.suki.ai/mcp.
Select Add.
When using Claude, select the attachments button and choose Suki Developer Documentation MCP server.

Install the MCP server with Claude Code CLI

Run the following command:

claude mcp add --transport http "Suki Developer Documentation MCP server" https://developer.suki.ai/mcp

Use the Documentation MCP dropdown in the top navigation bar to copy these snippets without retyping URLs or JSON.

Test your connection

After configuration, ask your AI tool:

What MCP tools do you have available?

You should see the Suki documentation search and get page tools listed. Then try:

Search the Suki documentation for ambient session webhooks

The AI should search and return relevant documentation pages.

Troubleshooting

MCP server not connecting

Verify the URL is exactly https://developer.suki.ai/mcp. Check your internet connection and restart your AI tool after configuration.

Search or get page tools not available

Confirm the MCP server was added correctly. Try removing and re-adding the server configuration. Check your AI tool’s MCP support documentation.

Search returns no results

Try different or more general search terms (for example, “webhook” instead of “session completion webhook payload”). Verify the MCP connection is active.

Additional context for AI tools

Use these URLs when an AI tool needs broader context than a single page:

Resource	URL	Use when
Documentation index	`llms.txt`	You need a list of all documentation pages with titles and descriptions
Full documentation	`llms-full.txt`	Your question spans multiple products (APIs, SDKs, webhooks, form filling, and more)
Integration skill	`skill.md`	You are building an agent or assistant that integrates Suki APIs or SDKs

Install the skill from your project:

npm

npx skills add https://developer.suki.ai

​Key benefits

Accelerate your development

Improve your LLM's responses

Reduce manual research

Reduce LLM hallucinations

​MCP server URL

​MCP server tools

​Search parameters

​Get page parameters

​How to set up MCP integration

​Test your connection

​Troubleshooting

​Additional context for AI tools

Key benefits

MCP server URL

MCP server tools

Search parameters

Get page parameters

How to set up MCP integration

Test your connection

Troubleshooting

Additional context for AI tools