mcp-teslamate-fleet
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.
README
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:
| Category | Tools | Backend |
|---|---|---|
| Status & History | tesla_status, tesla_drives, tesla_charging_history, tesla_battery_health, tesla_efficiency, tesla_location_history, tesla_state_history, tesla_software_updates |
TeslaMate |
| Analytics | tesla_savings, tesla_trip_cost, tesla_efficiency_by_temp, tesla_charging_by_location, tesla_top_destinations, tesla_longest_trips, tesla_monthly_summary, tesla_vampire_drain |
TeslaMate |
| Live Data | tesla_live |
Fleet API |
| Commands | tesla_climate_on/off, tesla_set_temp, tesla_charge_start/stop, tesla_set_charge_limit, tesla_lock, tesla_unlock, tesla_honk, tesla_flash, tesla_trunk, tesla_sentry |
Fleet API |
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:
- Register an app at developer.tesla.com
- Generate OAuth tokens — use Tesla's token generation flow
- Set up the HTTP proxy — commands must be signed using the Tesla Vehicle Command Protocol. Deploy the
tesla-http-proxyfrom 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
| Variable | Default | Description |
|---|---|---|
TESLAMATE_DB_HOST |
(required) | Postgres host |
TESLAMATE_DB_PORT |
5432 |
Postgres port |
TESLAMATE_DB_USER |
teslamate |
Postgres user |
TESLAMATE_DB_PASS |
(required) | Postgres password |
TESLAMATE_DB_NAME |
teslamate |
Database name |
Fleet API
| Variable | Default | Description |
|---|---|---|
TESLA_VIN |
(required) | Vehicle VIN |
TESLA_TOKEN_FILE |
(required) | Path to tokens.json with OAuth tokens |
TESLA_CLIENT_ID |
Fleet API client ID (for token refresh) | |
TESLA_CLIENT_SECRET |
Fleet API client secret (for token refresh) | |
TESLA_PROXY_URL |
HTTP proxy URL for commands | |
TESLA_FLEET_URL |
NA region | Fleet API endpoint (regional options) |
TESLA_VERIFY_SSL |
true |
Set false for self-signed proxy certs |
Vehicle Configuration
| Variable | Default | Description |
|---|---|---|
TESLA_CAR_ID |
1 |
TeslaMate car ID (for multi-car instances) |
TESLA_BATTERY_KWH |
75 |
Usable battery capacity in kWh |
TESLA_BATTERY_RANGE_KM |
525 |
EPA range at 100% in km |
Energy consumption is estimated from ideal range deltas using these values. Adjust for your vehicle:
| Vehicle | Battery (kWh) | Range (km) |
|---|---|---|
| Model 3 Standard Range | 54 | 350 |
| Model 3 Long Range | 75 | 500 |
| Model Y Long Range | 75 | 525 |
| Model S Long Range | 100 | 650 |
| Model X Long Range | 100 | 560 |
Cost Defaults
These are defaults — tesla_savings and tesla_trip_cost accept per-call overrides.
| Variable | Default | Description |
|---|---|---|
TESLA_ELECTRICITY_RATE |
0.12 |
Electricity cost in $/kWh |
TESLA_GAS_PRICE |
3.50 |
Gas price in $/gallon (for comparison) |
TESLA_GAS_MPG |
28 |
Comparable gas vehicle MPG |
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_idbut 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
drivestable 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.