What can you do with this server?

Access and analyze Tesla vehicle data through the Tessie API. * List all vehicles associated with the Tessie account * Retrieve current vehicle state including location, battery level, and odometer reading (with caching option) * Get driving history within specified date ranges with configurable limits * Find drives to specific locations with mileage information and date filtering * Calculate total miles driven during weekly or custom time periods

Which integrations are available for this server?

Provides access to Tesla vehicle data through the Tessie API, enabling queries about vehicle location, battery level, charging status, odometer readings, driving history, and mileage calculations using natural language.

How do I use Tessie MCP Extension?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Tessie MCP Extension how much battery do I have left and when should I charge?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Tessie MCP Server v2

MCP server rebuilt on the latest developer.tessie.com API. Summary-first tools, composite commands, and live-tested smoke scripts.

Quickstart

Install (Smithery recommended): npx -y @smithery/cli install @keithah/tessie-mcp
Set TESSIE_API_KEY (https://dash.tessie.com/settings/api) in your MCP client or .env. In Smithery UI the field appears as accessToken.
Try in a client: “List my vehicles” → get_active_context, “Lock VIN ...” → manage_vehicle_command with confirm: true.

Tools

get_active_context — vehicle roster with next-step guidance.
fetch_vehicle_state — locks, climate, battery, location snapshot.
fetch_vehicle_battery — charging-focused battery view.
search_drives — recent drives with optional date range.
get_driving_path — coordinate series for mapping/analysis.
manage_vehicle_command — lock/unlock, charging, climate, speed limit, sentry, cabin overheat, seat heat/cool, flash/honk, wake.

Command safety

Destructive operations require params.confirm: true.

{ "vin": "YOUR_VIN", "operation": "lock", "params": { "confirm": true } }

Non-destructive actions like flash_lights / honk skip confirmation.

Local dev & tests

Build stdio: npm run build:stdio
Build shttp: npm run build:shttp or npm run build:all
Tests: npm test (includes command validation)
Smoke with live Tessie token: npm run smoke (raw client), npm run smoke:tools (MCP tools)

Smithery

Playground/dev tunnel: npm run dev or npx @smithery/cli dev
Transports: stdio (npm run build:stdio), shttp (npm run build:shttp, default for publish)
Docs index: https://smithery.ai/docs/llms.txt ; TS quickstart: npx create-smithery@latest
Config schema: .well-known/mcp-config (expects TESSIE_API_KEY). Server card: .well-known/mcp.json (aliases in .well-known/mcp-server.json and .well-known/mcp/server.json).
Publish/update: npm run build:shttp → npx @smithery/cli publish (uses manifest.json). Ensure TESSIE_API_KEY is provided in user config.

Notes

API references cached in docs/llms-full.txt and docs/tessie-api-metadata.json for offline context.
Uses TypeScript MCP SDK and Tessie HTTPS API; all state stays in Tessie. Undo/confirmation is enforced in manage_vehicle_command.
MCP design references: see docs/glama-links.md for glama.ai best-practice articles.
Speed-limit operations accept speed_limit_pin (sensitive); avoid logging or sharing it.
Optional debug logging: set TESSIE_MCP_DEBUG=1 (or true) to emit request failures with URLs/status only (no headers/API keys); retry/backoff is built-in for 429/5xx responses.
Tessie client caches read requests (vehicles, state, battery, drives, paths, historical states) per client instance with short TTLs (15-30s), capped size (200 entries), and VIN-scoped invalidation after commands to avoid stale state while keeping token usage low.