teslamate-mcp MCP server

A Model Context Protocol (MCP) server that provides access to your TeslaMate database, allowing AI assistants to query Tesla vehicle data and analytics.

What teslamate-mcp does

Summarised from the project README; check the repository for the latest details.

Features

• Guidance for the assistant. MCP instructions and 11 prompts map questions to tools, and `getunitpreferences` lets the assistant answer in the units set in TeslaMate.
• Safe custom SQL. `runsql` runs your `SELECT` inside a PostgreSQL `READ ONLY` transaction, with timeouts and a row cap. The transaction always rolls back.
• Optional cost writes, with confirmation. One opt-in tool writes charging costs. A column-scoped database grant limits what it can touch. Clients with MCP elicitation show a confirmation dialog first.
• Local-time reports. Set `REPORTTIMEZONE` and daily, weekly, and monthly buckets follow your local midnight.
• Two transports. Run `teslamate-mcp stdio` for local clients. Run `teslamate-mcp http` for remote clients, with bearer-token auth and a `/health` probe.

Tools exposed (20+)

• Group – Tools
• Vehicle – `getbasiccarinformation`, `getcurrentcarstatus`, `getsoftwareupdatehistory`, `getunitpreferences`
• Battery – `getbatteryhealthsummary`, `getbatterydegradationovertime`, `getdailybatteryusagepatterns`, `gettirepressureweeklytrends`
• Driving – `getmonthlydrivingsummary`, `getdailydrivingpatterns`, `getlongestdrivesbydistance`, `gettotaldistanceandefficiency`, `getdrivesummaryperday
• Efficiency – `getefficiencybymonthandtemperature`, `getaverageefficiencybytemperature`, `getefficiencybyelevation`, `getdriveefficiencypoints`, `getunusu
• Charging – `getchargingbylocation`, `getallchargingsessionssummary`, `getmostvisitedlocations`
• get_battery_capacity_trend – Usable capacity in kWh, estimated from charging sessions (energy added ÷ SOC gained), per month and car
• get_vampire_drain – Range lost while parked between drives; gaps that contain a charge do not count
• get_charging_efficiency – kWh added vs kWh drawn per car, split into AC and DC
• get_charging_by_geofence – Charging totals per TeslaMate geofence, plus an "Ungeofenced" group
• get_soc_hygiene – Share of samples above 80% and below 20% state of charge
• get_period_comparison – The last N days vs the N days before, one row per metric
• get_activity_report – A month by day or a year by month: drives, distance, consumption, charging, and cost per bucket, empty days included
• get_trip_energy_estimate – "Will I make it?": energy and battery % a drive of a given distance takes, from this car's own drives at a similar temperature (optionally m
• get_timeline – What the car did, in order: drives, charges, the time parked between them, and software updates, with places, battery %, kWh, and cost; answ
• get_state_history – Per car and local day: hours online, asleep, and offline, driving and charging hours, idle awake hours (online while parked and not charging
• get_idle_awake_periods – The online periods that kept the car awake while parked, longest first, with where it was parked; answers "why isn't my car sleeping?"
• search_drives – Drives filtered by date range, location text, distance, and car; sortable
• search_charging_sessions – Charging sessions filtered by date range, location, energy, and car
• get_drive_details – Full statistics for one drive

Requirements

• TeslaMate with its PostgreSQL database.
• Python 3.11+ for a local install, or Docker for a server install.

How to install teslamate-mcp

Listed on Socketlist – add this badge to your README:

Badge markdown[](https://socketlist.pages.dev/s/cobanov-teslamate-mcp/)

Maintain this project? Get it featured for free during launch →

Compare with codebase-memory-mcp →

Related Databases MCP servers