Building with AI
Use AI tools in your Fintoc integration workflow.
You can use AI to help build your Fintoc integration. This page lists the tools Fintoc exposes for AI-assisted integration. These tools include the in-product Ask AI dropdown, plain-text and llms.txt access to the docs, the Fintoc CLI, two MCP servers, and a set of Agent Skills.
Ask AI dropdown
Open the Ask AI dropdown 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 Ask AI dropdown to copy any documentation page as markdown and paste it into other AI tools, IDEs, or documents with its formatting preserved.
This format helps AI tools and agents consume Fintoc's content and lets you copy the entire contents of a doc into a large language model (LLM). It is preferable to scraping or copying from Fintoc's 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.
- The plain text version includes content the default view hides, such as text inside a tab.
- LLMs can parse and understand markdown hierarchy.
llms.txt
Fintoc also hosts an /llms.txt file that tells AI agents how to retrieve the plain text versions of Fintoc's 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 servers provide a set of tools that AI agents can use to interact with the Fintoc API and search Fintoc's knowledge base, including the documentation.
Agent Skills
Fintoc's Agent Skills give coding agents like Claude Code and Cursor context and best practices for building with Fintoc. Install them with npx skills add fintoc-com/agent-skills.