Bring Connected Vehicle
to Vercel AI SDK
Learn how to connect General Motors to Vercel AI SDK and start using 14 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for Subscribers
What is the General Motors MCP Server?
What you can do
Connect AI agents to the General Motors Connected Vehicle API for comprehensive car management:
- List registered vehicles to manage fleets or personal garages
- Track GPS location to find parked cars or monitor fleet movement
- Monitor diagnostics including oil life, battery voltage, and check engine status
- Check EV charge levels and estimated range for electric vehicles
- Lock and unlock doors remotely for security or guest access
- Start and stop engines remotely to pre-condition cabin temperature
- Flash lights and sound horn to locate vehicles in crowded areas
- Send navigation destinations directly to the infotainment system
How it works
1. Register at GM Developer Portal and create an application
2. Authenticate via OAuth to obtain an access token for your vehicle
3. Ask your AI agent to check status, run diagnostics, or send commands
4. Natural language commands replace the myChevrolet/OnStar app navigation
Who is this for?
Perfect for GM vehicle owners, fleet managers, service advisors, and roadside assistance teams. Let AI agents automate morning warm-ups, monitor tire pressure for safety, track mileage for maintenance schedules, and locate vehicles. Ideal for drivers who want to integrate their car into their smart home or AI assistant workflow for seamless mobility management.
Built-in capabilities (14)
Requires VIN. Use this to locate a vehicle in a crowded parking lot or driveway. Trigger the horn of a GM vehicle to locate it
Requires VIN. Use this to locate a vehicle in the dark or signal ownership. Flash the headlights and taillights of a GM vehicle
Requires VIN. Use this to manage EV range anxiety or schedule charging during off-peak hours. Get the charging status and battery level of a GM EV (Bolt, Ultium, etc)
Requires VIN. Use this to plan refueling stops or monitor fuel economy. Get the current fuel tank level of a GM vehicle
Requires VIN. Use this to track service intervals, lease mileage limits, or fleet utilization. Get the current mileage (odometer reading) of a GM vehicle
Requires VIN. Use this to identify leaks, ensure safety, or prepare for long trips. Get the current tire pressure readings for all four tires
Requires VIN. Use this for maintenance scheduling, pre-trip inspections, or health monitoring. Get comprehensive diagnostic data for a GM vehicle
Requires VIN. Use this to find your parked car, track fleet assets, or verify vehicle movement. Get the current GPS location of a specific GM vehicle
Use this as the first step to identify which VIN to use for commands or diagnostics. List all GM vehicles associated with the account
Requires VIN. Returns command status (success/failed/in-progress). Use this to secure the vehicle after parking or if you forgot to lock it. Lock the doors of a specific GM vehicle remotely
Requires VIN and a destination object with latitude, longitude, and address. Use this to plan a trip on your phone and have it ready in the car. Send a destination to the vehicle's built-in navigation system
Requires VIN. Returns command status. Use this to warm up the car in winter or cool it down in summer before entering. Remotely start the engine of a GM vehicle
Requires VIN. Returns command status. Use this to cancel a remote start if the vehicle is now in use or if there is a safety concern. Remotely stop the running engine of a GM vehicle
Requires VIN. Returns command status. Use this to let a passenger in or if keys are locked inside. Unlock the doors of a specific GM vehicle remotely
Why Vercel AI SDK?
The Vercel AI SDK gives every General Motors tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 14 tools through Vinkius and stream results progressively to React, Svelte, or Vue components. works on Edge Functions, Cloudflare Workers, and any Node.js runtime.
- —
TypeScript-first: every MCP tool gets full type inference, IDE autocomplete, and compile-time error checking out of the box
- —
Framework-agnostic core works with Next.js, Nuxt, SvelteKit, or any Node.js runtime. same General Motors integration everywhere
- —
Built-in streaming UI primitives let you display General Motors tool results progressively in React, Svelte, or Vue components
- —
Edge-compatible: the AI SDK runs on Vercel Edge Functions, Cloudflare Workers, and other edge runtimes for minimal latency
General Motors in Vercel AI SDK
General Motors and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect General Motors to Vercel AI SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for General Motors in Vercel AI SDK
The General Motors MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 14 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Vercel AI SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
General Motors for Vercel AI SDK
Every tool call from Vercel AI SDK to the General Motors MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Which vehicles are supported by this MCP server?
This MCP server supports GM vehicles from model year 2015 and newer that are equipped with OnStar connectivity. This includes most Chevrolet, GMC, Buick, and Cadillac models. You can verify compatibility by checking if your vehicle has the OnStar button or the myChevrolet/myGMC/myBuick/myCadillac app support.
Do I need an active OnStar subscription to use this server?
Yes, an active OnStar subscription is required to access the GM Connected Vehicle API. The specific features available depend on your OnStar plan. Remote commands like lock/unlock, remote start, and diagnostics require a plan that includes those capabilities. Check your OnStar plan details at my.chevrolet.com or contact OnStar support for more information.
How are vehicle commands secured?
All vehicle commands are authenticated through the GM Developer Portal OAuth flow. Each command requires a valid access token tied to your GM account. The MCP server does not store credentials; it uses the token provided during setup. Only vehicles linked to your GM account can be controlled, and all commands are logged in the OnStar activity history for audit purposes.
How does the Vercel AI SDK connect to MCP servers?
Import createMCPClient from @ai-sdk/mcp and pass the server URL. The SDK discovers all tools and provides typed TypeScript interfaces for each one.
Can I use MCP tools in Edge Functions?
Yes. The AI SDK is fully edge-compatible. MCP connections work on Vercel Edge Functions, Cloudflare Workers, and similar runtimes.
Does it support streaming tool results?
Yes. The SDK provides streaming primitives like useChat and streamText that handle tool calls and display results progressively in the UI.
createMCPClient is not a function
Install: npm install @ai-sdk/mcp