Skip to main content
This guide walks you from a brand-new Chiplab account to a completed firmware simulation. By the end, your AI coding agent will be connected to Chiplab and you will have seen real stdout output from a virtual chip instance — no physical hardware required.
1

Sign in to Chiplab

Go to chiplab.veecle.ai and sign in with your account.
2

Connect your agent

Navigate to API Keys in the sidebar, then click Connect agent. Select your agent from the list — Cursor, OpenCode, Codex, GitHub Copilot or Claude Code — and follow the instructions displayed on screen.Each agent requires a short configuration step to register Chiplab MCP server, followed by a browser-based authentication step. The dashboard shows the exact commands and config snippets for your chosen agent.
3

Ask your agent to use Chiplab

Once connected, you don’t need to call any tools yourself. Just tell your agent what you want, in plain language, and it takes care of the rest.For example:
Test this on Chiplab: /path/to/my/firmware.elf on an STM32F4 Discovery board
Your agent uploads the binary, runs it on a chip-accurate virtual board, and reports back the output. You can also ask more open-ended things, like:
I just built this firmware for the nRF52840. Can you run it on Chiplab and tell me if the UART output looks right?
4

Ask questions about Chiplab

Your agent can also query Chiplab directly, for example if it needs to know which boards are supported or how a specific tool works. You don’t need to prompt this explicitly. It happens automatically when your agent needs context, most commonly the first time it uses Chiplab in a session.

​
Connect your agent

Follow the guide for your specific agent to complete the connection setup.

Connect Cursor

Configure Chiplab in Cursor’s MCP settings and authenticate.

Connect OpenCode

Register Chiplab in your OpenCode config and run the auth command.

Connect Claude Code

Add Chiplab via the Claude CLI and authenticate with /mcp.