TeslaMate + Fleet API MCP Server

MCP server combining TeslaMate historical analytics with Fleet API live data and commands. Works with Claude Code, Claude Desktop, Cursor, and any MCP-compatible client.

The first MCP server to bring both data sources together — use TeslaMate for deep analytics and Fleet API for real-time control, or configure just one.

Features

29 tools across four categories:

Safety: unlock and trunk commands require confirm=True. All commands are rate-limited to 40/day.

Quick Start

Claude Code (.mcp.json)

{
  "mcpServers": {
    "tesla": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/lodordev/mcp-teslamate-fleet", "mcp-teslamate-fleet"],
      "env": {
        "TESLAMATE_DB_HOST": "localhost",
        "TESLAMATE_DB_PASS": "your_password",
        "TESLA_VIN": "your_vin",
        "TESLA_TOKEN_FILE": "/path/to/tokens.json",
        "TESLA_CLIENT_ID": "your_client_id",
        "TESLA_CLIENT_SECRET": "your_client_secret",
        "TESLA_PROXY_URL": "https://localhost:4443",
        "TESLA_VERIFY_SSL": "false"
      }
    }
  }
}

Claude Desktop (claude_desktop_config.json)

Same structure — add under mcpServers.

Local install

git clone https://github.com/lodordev/mcp-teslamate-fleet
cd tesla-mcp
pip install -e .

Prerequisites

You need at least one of these backends configured. Both is ideal.

TeslaMate (analytics + history)

TeslaMate is an open-source Tesla data logger. It records driving, charging, and vehicle state to a Postgres database.

If you already run TeslaMate, you just need the database connection details. If not, see the TeslaMate installation guide.

Fleet API (live data + commands)

Tesla's Fleet API provides real-time vehicle data and remote commands. Setup requires:

1. Register an app at developer.tesla.com

2. Generate OAuth tokens — use Tesla's token generation flow

3. Set up the HTTP proxy — commands must be signed using the Tesla Vehicle Command Protocol. Deploy the tesla-http-proxy from that repo

The proxy is only needed for commands (tesla_climate_on, tesla_lock, etc.). tesla_live works with just a token.

Tesla provides a $10/month free credit for Fleet API, which is more than enough for personal MCP use.

Configuration

All configuration is via environment variables.

TeslaMate Database

Fleet API

Vehicle Configuration

Energy consumption is estimated from ideal range deltas using these values. Adjust for your vehicle:

Cost Defaults

These are defaults — tesla_savings and tesla_trip_cost accept per-call overrides.

Architecture

Single-file Python server (~1400 lines) using FastMCP. Two data paths:

┌─────────────┐     ┌──────────────┐
│  TeslaMate   │────▶│   Postgres   │──┐
│  (logger)    │     │  (telemetry) │  │
└─────────────┘     └──────────────┘  │   ┌───────────┐     ┌────────────┐
                                       ├──▶│ tesla.py  │────▶│ MCP Client │
┌─────────────┐     ┌──────────────┐  │   │ (server)  │     │ (Claude,   │
│  Tesla       │────▶│ HTTP Proxy   │──┘   └───────────┘     │  Cursor)   │
│  Fleet API   │     │ (commands)   │                         └────────────┘
└─────────────┘     └──────────────┘

Limitations

• Single vehicle — queries use a configurable car_id but tools don't accept it as a parameter. Multi-car users should run separate server instances.

• Imperial units — output is in miles, °F, and PSI. Metric support is planned.

• Estimated kWh — TeslaMate's drives table doesn't include energy consumed directly. We estimate from ideal range deltas using your configured battery capacity. Accuracy is ~90-95%.

Credits

Inspired by cobanov/teslamate-mcp. Built with FastMCP and TeslaMate.

License

MIT