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’ll have seen real UART 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. It’s self-serve: no credit card needed, and there’s a free tier to get you started.
2

Connect your agent

Navigate to API Keys in the sidebar, then click Connect agent. Select your agent from the list, Cursor, OpenCode, Claude Code, and others, and follow the instructions on screen.Each agent needs a short configuration step to register the Chiplab MCP server (https://chiplab.veecle.ai/mcp), followed by a browser-based authentication step. The dashboard shows the exact commands and config snippets for your chosen agent, or see the per-agent guides below.If you’re working from a clone of this repo, some agents are pre-configured: Claude Code picks up .mcp.json automatically and just prompts you to trust it. Otherwise, add Chiplab like any other MCP server; see Connect your agent below for the exact config for your client. On first use your client opens a browser to sign in.
3

Build and run an example

With your agent connected, verify the connection by asking it to call Chiplab’s ask tool with no arguments; it should come back with a platform overview.Then try a real simulation. Clone this repo:
git clone https://github.com/veecle/chiplab && cd chiplab
Then just tell your agent:
Build and run examples/bare-metal/stm32f4-discovery on Chiplab.
Your agent installs what’s needed, builds the binary, uploads the ELF, and runs it on a virtual STM32F4 Discovery board. The run returns synchronously, bounded to a fixed amount of virtual time, and you’ll see Hello world! in the captured UART output.This same produce-an-ELF → upload → run → read-output flow works for every board and framework this repo ships examples for; only the ELF path and board change. See supported-boards.md for the full board list.
4

Ask questions about Chiplab

Your agent can also query Chiplab directly; you don’t need to prompt this explicitly. It happens automatically whenever your agent needs context, most commonly the first time it uses Chiplab in a session.

​
Connect your agent

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.

Other agents

Claude Desktop, VS Code, Codex, and any other MCP-capable client.