Building with AI

You can use AI to assist in the building of your Fintoc integration. This guide covers the tools Fintoc exposes for AI-assisted integration and the practices that keep agent-driven development reliable.

Ask AI dropdown

Ask Fintoc's documentation a question with the Ask AI dropdown on any guide page. Open the AI menu on any guide page to ask questions about the API, request code samples, or copy the page in plain text.

Plain text docs

You can also use the dropdown to easily copy any documentation page in markdown format, making it simple to paste into other AI tools, IDEs, or documents while preserving formatting.

This helps AI tools and agents consume our content and allows you to copy and paste the entire contents of a doc into an LLM. This format is preferable to scraping or copying from our HTML and JavaScript-rendered pages because:

• Plain text strips HTML and JavaScript wrappers, so the page fits in the model's context window without rendering overhead.
• Content that isn’t rendered in the default view (for example, it’s hidden in a tab) of a given page is rendered in the plain text version.
• LLMs can parse and understand markdown hierarchy.

llms.txt

Fintoc also hosts an /llms.txt file which tells AI agents how to retrieve the plain text versions of our pages. The /llms.txt file is an emerging standard for making websites and content more accessible to LLMs.

Command Line Interface (CLI)

AI agents such as Claude Code, Cursor, and Codex can drive the Fintoc CLI directly. You can use the Fintoc CLI to make API requests and listen to webhooks from the command line

Model Context Protocol (MCP)

The Fintoc MCP server enables AI-powered code editors like Cursor and Claude Code, plus general-purpose tools like Claude Desktop, to interact directly with Fintoc's documentation.

Set up the Fintoc MCP server

Fintoc hosts a remote MCP server at https://docs.fintoc.com/mcp. Configure your AI agent to connect to this server.

{
  "mcpServers": {
    "fintoc": {
      "url": "https://docs.fintoc.com/mcp"
    }
  }
}

Test your MCP setup

Test your MCP setup:

1. Open your AI editor (Cursor, VS Code, etc.)
2. Start a new chat with the AI agent
3. Ask about Fintoc - try questions like:
   • "Show me an example of how to create a Checkout Session in Python with the Fintoc API"
   • "Generate a JWS signature for the Fintoc API in Java"
   • "Which endpoint cancels a refund in Fintoc?"

The AI should now have access to the Fintoc documentation through the MCP server.