Skip to main content
Chiplab exposes its simulation capabilities through the Model Context Protocol (MCP). Once your agent is connected, it can call tools like ask and run directly inside a chat or terminal session, no manual API calls, no context switching, no physical board required.

How it works

Chiplab acts as an MCP server; your coding agent acts as the MCP client. When you send a message that involves firmware simulation, your agent automatically discovers the available tools and calls them on your behalf. Authentication happens once via a browser-based OAuth flow; you never need to copy tokens or manage credentials manually.

MCP server URL

Chiplab’s MCP server is available at https://chiplab.veecle.ai/mcp. This URL is public and requires no special handling. Authentication happens separately, through your browser session.

Choose your agent

Cursor

Add Chiplab to Cursor’s MCP settings and run firmware simulations from the editor’s AI chat panel.

OpenCode

Register Chiplab as a remote MCP server in OpenCode and authenticate from your terminal.

Claude Code

Register Chiplab as an HTTP MCP server in the Claude Code CLI and connect in a single command.

Claude Desktop

Add Chiplab as a connector in Claude Desktop and authenticate in the browser.

VS Code

Register Chiplab in VS Code’s MCP config and use it from Copilot’s agent mode.

Codex

Add Chiplab to the Codex CLI’s TOML config and sign in with one command.
These guides cover Chiplab’s most-used clients, but Chiplab isn’t limited to them — it works with any MCP-capable client. GitHub Copilot and others connect to the same server URL above using their client’s standard MCP configuration.

Managing connected sessions

After you complete the authentication flow, your agent session appears on the API Keys page of the Chiplab dashboard under Connected agents. From there you can:
  • See when the agent first connected and when it was last active.
  • Revoke any session instantly; the agent loses access immediately and must re-authenticate to reconnect.
Revoking is useful when you rotate machines, hand off a project, or suspect a session has been exposed.