← All guides
AI

AI coding tools

Pick the tool you build in. Each guide walks you through configuration, the first verified prompt, common workflows and what to do when something breaks.

Which artifact does your tool use?

Every project ships four artifacts from its Connect page. Different tools consume different ones — picking right is the difference between "wired up in 60 seconds" and "fighting context all afternoon."

Tool Primary artifact Why
Cursormcp.jsonNative MCP support; tools appear in the agent toolbar.
Claude Code.mcp.jsonNative MCP support; agent can call your platform tools.
Windsurfmcp_config.jsonCascade calls the platform tools mid-flow.
v0.devllms.txtNo MCP yet — paste the brief as up-front context.
Lovablellms.txtPin the brief as a knowledge document.
Boltllms.txt + SDKDrop the brief into the first prompt; the SDK ships with the generated project.
Cu
Editor · MCP

Cursor

Per-workspace .cursor/mcp.json that registers every endpoint of your project as a tool the agent can call directly from chat or Composer.

Open guide →
C
Terminal · MCP

Claude Code

Drop .mcp.json at the repo root, export the API key, and Claude gets first-class access to your schema and endpoints from the CLI.

Open guide →
Ws
Editor · MCP · Cascade

Windsurf

Paste the MCP config in Windsurf settings, and Cascade can change your schema and write the matching client code in a single flow.

Open guide →
v0
Prompt · llms.txt

v0.dev

Paste llms.txt as the leading context block so v0 generates components that fetch from real endpoints with the right shape and auth header.

Open guide →
Lo
Prompt · pinned context

Lovable

Pin llms.txt as a knowledge document so every iteration sees the real backend, and pair it with a small init snippet for the chisel.to client.

Open guide →
Bo
Prompt · full stack

Bolt

Front-load llms.txt and ask Bolt to scaffold a full-stack project that calls your chisel.to backend, with auth, data and realtime wired from the start.

Open guide →
Using a different tool? Anything that supports the open Model Context Protocol can load chisel.to's mcp.json. For prompt-only tools (Replit AI, ChatGPT Canvas, etc.), the llms.txt brief works the same way it does for v0 and Lovable.