Our MCP servers give your AI coding assistant direct access to KeyLines, ReGraph, KronoGraph, and MapWeave documentation. Get working visualization code, not generic JavaScript.
Join our workshop or watch Ivan’s demo to see it in action.
See what’s possible
With access to our MCP server, the AI can query ReGraph documentation in real-time, understand our SDK’s structure, and generate working code that follows our best practices. What you’re watching would typically take 2-3 hours of manual coding and documentation look-up.
Why this matters
- AI assistants query our documentation in real-time
- Generate SDK-specific code that actually runs
- Works with VS Code, Cursor, JetBrains, and other MCP-compatible IDEs
AI coding assistants like GitHub, Copilot, and Cursor are great at general JavaScript, but they struggle with specialized SDKs. Our MCP (Model Context Protocol) servers solve this by giving these AI tools direct access to our documentation, type definitions, and examples.
When you ask your AI assistant to build a graph visualization, it can query the actual KeyLines documentation and generate code that works. No more guessing, no more debugging AI-generated code that doesn’t match our API.
Join our live workshop on January 27
We’ll demonstrate how to set up and use MCP servers with our SDKs, and you can follow along to build your own prototype.
Why join this session?
- Learn how to configure your IDE so your code assistant can connect to the MCP servers
- See some of our initial findings on best practice for working with code assistants and our SDKs
- You might even walk away with a working prototype to wow your colleagues!
This event is for customers and evaluators only – so if you’re not already using our SDKs, request a free trial
Get started
Use the MCP server with the SDK that fits your application. Each SDK has its own getting started guide and examples:
FAQ
What is MCP?
Model Context Protocol is an open standard (like USB-C for AI) that lets AI coding assistants connect to external documentation and tools. Think of it as giving your AI assistant the ability to “read the manual” while helping you code.
Do I need access to more than one SDK?
No, each SDK has its own MCP server. Use the one(s) relevant to your project – KeyLines for graphs, ReGraph for React-based graphs, KronoGraph for timelines, MapWeave for geospatial visualization.
Which tools does this work with?
Any IDE or AI assistant that supports MCP – including VS Code with GitHub Copilot, Cursor, JetBrains, Claude Code, and more. As long as your tool can connect to MCP servers, it will work.
Is my code and data secure?
MCP servers only provide read access to our public documentation. Your code stays in your development environment. The MCP protocol lets your AI assistant query our documentation – no proprietary code or data is sent to our servers.
When will this be available?
We’re offering limited early access. Join the January 27 workshop or sign up for our waiting list to be notified when it’s ready for your team.
