chiplab

Chiplab gives AI coding agents direct access to chip-accurate firmware simulation — no physical hardware required.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Ask: Query the Chiplab knowledge base with a natural language question. This can be used to get help about what Chiplab is, how to use it etc. For a general overview, read `/mcp/resources/docs/overvie
  • Cancel Task: Cancel a currently running task
  • Get Task Info: Check the current lifecycle status of the task

What data it sees

Do you need an account

No: the server works without sign-in

Chiplab gives AI coding agents direct access to chip-accurate firmware simulation — no physical hardware required. Connect your agent once, then just describe what you want in plain language ("test this firmware on an STM32"), and Chiplab handles the rest: building, uploading, running on a virtual board, and reporting back the results.

How to connect

How to connect chiplab to Claude

The server address to paste into Claude settings:

https://chiplab--veecle.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect chiplab to ChatGPT

The server address to paste into ChatGPT settings:

https://chiplab--veecle.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect chiplab to Cursor

The server address to paste into Cursor settings:

https://chiplab--veecle.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (8)

Raw names from tools/list. Only developers need these.

askQuery the Chiplab knowledge base with a natural language question. This can be used to get help about what Chiplab is, how to use it etc. For a general overview, read `/mcp/resources/docs/overview.md` directly instead of calling this tool. URLs containing `/mcp/resources/` in responses correspond to MCP resources on this server, if you have MCP resource tools use them, otherwise use a normal web fetch.
cancel_taskCancel a currently running task
get_task_infoCheck the current lifecycle status of the task
get_task_resultGet the task's result, blocking if not yet ready
issue_download_ticketIssue a time-limited, presigned URL to download an artifact produced by a firmware simulation run without further authentication. This tool requires a `run_id` previously obtained from the `run` tool and an `artifact_name` as listed by the `list_run_artifacts` tool. The returned `download_url` accepts a raw `GET` request and responds with the artifact bytes as the body (e.g. `curl DOWNLOAD_URL`).
issue_upload_ticketIssue a time-limited, presigned URL to upload an artifact without further authentication. The returned `upload_url` accepts a raw `PUT` request with the artifact bytes as the body (e.g. `curl --upload-file firmware.elf UPLOAD_URL`). The `artifact_id` field is the identifier to pass to tools consuming uploaded artifacts once the upload has completed.
list_run_artifactsList every artifact produced by a firmware simulation run. This tool requires a `run_id` previously obtained from the `run` tool. The response lists the location of each artifact the run generated. To read the content of a listed artifact, pass its name to the `issue_download_ticket` tool.
runRun a new firmware simulation on the given board. This tool requires an `artifact_id` previously obtained from the `issue_upload_ticket` tool. The response from that tool also includes the URL the artifact must be uploaded to before this tool is called. Use the Ask tool for further details about uploading artifacts. Once the triggered task responds with OK, the response contains the list of output artifacts generated by the run. This list may be empty if the run produced no output artifacts. You can query the same list again at any time using the `list_run_artifacts` tool with the corresponding `run_id`.