ChatGPT

ChatGPT can connect to remote MCP servers as connectors. Point it at the Teslemetry endpoint and authorize with OAuth — no tokens to copy.

https://api.teslemetry.com/mcp

ChatGPT app

Custom connectors are available to ChatGPT Plus, Pro, Business and Enterprise users. You may need to enable Developer mode under Settings → Connectors → Advanced first.

1. Open Settings → Connectors.
2. Click Create (or Add custom connector).
3. Give it a name (e.g. Teslemetry) and enter the URL https://api.teslemetry.com/mcp.
4. Choose OAuth authentication and click Create.
5. Complete the Teslemetry sign‑in and approve access.

Once connected, enable the Teslemetry connector in a chat (via the + / tools menu) and ask ChatGPT to read or control your Tesla — for example "Is my car charging?" or "Set the charge limit to 80%."

OpenAI API

When building your own agents with the OpenAI Responses API or Agents SDK, add Teslemetry as a remote MCP tool. For unattended use, authenticate with a Teslemetry access token as a bearer header instead of the interactive OAuth flow:

from openai import OpenAI

client = OpenAI()

response = client.responses.create(
    model="gpt-5",
    tools=[
        {
            "type": "mcp",
            "server_label": "teslemetry",
            "server_url": "https://api.teslemetry.com/mcp",
            "headers": {
                "Authorization": "Bearer YOUR_TESLEMETRY_TOKEN"
            },
            "require_approval": "always",
        }
    ],
    input="What is the battery level of my Tesla?",
)

print(response.output_text)

Troubleshooting

• Connector won't add — confirm your plan supports custom connectors and that Developer mode is enabled.
• Commands fail but reads work — your vehicle likely needs a virtual key.
• "No products found" — make sure you have an active subscription and a connected Tesla product.