Connects to the Tesla Fleet API to retrieve vehicle information and control Tesla vehicles, providing functionality to wake up vehicles from sleep mode and get detailed vehicle information
Tesla MCP Server
A Model Context Protocol (MCP) server that connects to the Tesla Fleet API, allowing you to control your Tesla vehicle using Claude and other AI assistants that support MCP.
Features
Wake up vehicles: Wake up your Tesla from sleep mode
Vehicle information: Get detailed information about your Tesla vehicles
Real-time updates: Refresh vehicle data on demand
Debugging tools: Access detailed vehicle information to help with troubleshooting
Requirements
Node.js 18+
pnpm (preferred) or npm
Tesla account with at least one vehicle
Tesla API credentials (Client ID and Client Secret)
Ngrok (for development and registration)
Security Best Practices
This project handles sensitive Tesla API credentials. Please follow these security practices:
Never commit credentials: The
.gitignore
file excludes.env
andkeys/
but always double-checkUse the security checker: Run
./check-secrets.sh
before committing to detect potentially leaked credentialsProtect your private keys: Keep the contents of the
keys/
directory secureReview code before sharing: Make sure no credentials are hardcoded in any source files
When forking or sharing this project:
Make sure the
.env
file is not includedCheck that no private keys are committed
Verify the
.gitignore
file is properly set up
Quick Start
Clone the repository
git clone https://github.com/yourusername/tesla-mcp.git cd tesla-mcpInstall dependencies
pnpm installSet up environment variables Create a
.env
file in the root directory:TESLA_CLIENT_ID=your_client_id TESLA_CLIENT_SECRET=your_client_secret TESLA_REFRESH_TOKEN=your_refresh_tokenGet a refresh token (if you don't have one)
pnpm get-tokenRegister your application with Tesla's API
pnpm registerFollow the instructions provided by the script
Build the server
pnpm buildRun the server
pnpm start
Authentication & Registration
This project uses the official Tesla Fleet API OAuth 2.0 authentication flow to securely connect to your Tesla account. The full process involves two steps:
Authentication: Obtaining a refresh token through the OAuth 2.0 flow
Registration: Registering your application with Tesla via the Partner Accounts API
Authentication
Authentication requires:
Client ID and Client Secret from the Tesla Developer Portal
A refresh token obtained through the OAuth 2.0 authorization code flow
The included pnpm get-token
utility simplifies this process by:
Opening a browser for you to log in with your Tesla account credentials
Performing the OAuth PKCE (Proof Key for Code Exchange) flow
Exchanging the authorization code for refresh and access tokens
Storing the refresh token in your
.env
file
Registration
The Tesla Fleet API requires applications to be registered before they can access vehicle data. The registration server (pnpm register
) automates this process:
Generates the required EC key pair
Uses ngrok to create a temporary public URL for development
Hosts the public key at the required path
Handles the registration API call with Tesla
Ngrok Setup (Required for Registration)
Install ngrok from ngrok.com/download
Create a free account at ngrok.com
Get your auth token from the ngrok dashboard
Authenticate ngrok:
ngrok authtoken YOUR_AUTH_TOKEN
Available MCP Tools
The server provides the following tools that Claude can use:
wake_up
: Wakes up a Tesla vehicle from sleep modeTakes
vehicle_id
as a required parameterReturns the current state of the vehicle
refresh_vehicles
: Refreshes the list of Tesla vehiclesNo parameters required
Updates the internal cache of vehicles
debug_vehicles
: Shows detailed information about available vehiclesNo parameters required
Returns ID, vehicle_id, VIN, and state information
Setting Up Claude to Use the MCP Server
Create the Claude configuration directory:
mkdir -p ~/Library/Application\ Support/ClaudeCreate or edit the configuration file:
nano ~/Library/Application\ Support/Claude/claude_desktop_config.jsonAdd the following configuration (adjust the path as needed):
{ "mcpServers": { "tesla-mcp-server": { "command": "/absolute/path/to/tesla-mcp/run-mcp.js" } } }Make the run-mcp.js script executable:
chmod +x run-mcp.jsRestart Claude completely
Using the MCP Server with Claude
Once the server is running and Claude is configured, you can ask Claude to:
"What Tesla vehicles do I have?"
"Can you wake up my Tesla?"
"Show me debug information about my Tesla vehicles"
Troubleshooting
If you encounter issues:
Environment Variables
Ensure your
.env
file contains valid credentialsRun
pnpm get-token
to refresh your token if needed
Server Connection
Check that the server is running (
pnpm start
)Verify Claude's configuration points to the correct file path
Vehicle Connectivity
Vehicle might be offline or asleep
Try waking up the vehicle first with the
wake_up
command
Debug Mode
Use the
debug_vehicles
command to get detailed information about your vehiclesCheck the server logs in the terminal where you're running the MCP server
Command Line Tools
The server includes several helpful scripts:
pnpm build
: Compile the TypeScript codepnpm start
: Run the server using the run-mcp.js scriptpnpm register
: Register your app with Tesla's APIpnpm get-token
: Get a refresh token from Teslapnpm test-api
: Test your connection to the Tesla APIpnpm inspector
: Run the server with the MCP Inspector for debugging
API Limitations
As of 2023-10-09, Tesla has deprecated many vehicle command endpoints in their REST API. Commands like honking the horn now require the Tesla Vehicle Command Protocol instead of the REST API. This MCP server currently supports only REST API endpoints that remain functional.
Future Enhancements
Possible future improvements include:
Integration with Tesla's Vehicle Command Protocol for additional commands
Support for more vehicle information endpoints
User interface for configuration and monitoring
License
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
A Model Context Protocol server that connects to the Tesla Fleet API, allowing AI assistants like Claude to control Tesla vehicles and access vehicle information through natural language commands.
- Features
- Requirements
- Security Best Practices
- Quick Start
- Authentication & Registration
- Available MCP Tools
- Setting Up Claude to Use the MCP Server
- Using the MCP Server with Claude
- Troubleshooting
- Command Line Tools
- API Limitations
- Future Enhancements
- License
Related Resources
Related MCP Servers
- -securityFlicense-qualityA Model Context Protocol server that allows Claude to make API requests on your behalf, providing tools for testing various APIs including HTTP requests and OpenAI integrations without sharing your API keys in the chat.Last updated -
- AsecurityAlicenseAqualityA Model Context Protocol server that enables AI assistants like Claude to interact directly with Home Assistant, allowing them to query device states, control smart home entities, and perform automation tasks.Last updated -12191MIT License
- -securityFlicense-qualityA Model Context Protocol server that extends AI capabilities by providing file system access and management functionalities to Claude or other AI assistants.Last updated -3436
- AsecurityAlicenseAqualityA Model Context Protocol server that enables AI models like Claude to control TeamSpeak servers, allowing users to manage channels, send messages, configure permissions, and perform server administration through natural language commands.Last updated -406MIT License