About Getting Started
Getting Started is a minimal TanStack Start MCP server example. It shows how to run the application and connect to its local SSE endpoint using `mcp-remote`.
Key features
- 01Run with `pnpm i` and `pnpm dev`
- 02Expose a local SSE endpoint
- 03Connect through `mcp-remote`
Use cases
- 01Try a TanStack Start MCP example locally
- 02Configure an MCP connection to the local SSE endpoint
MCP support
The example provides a local `/api/sse` endpoint and documents connecting to it with `mcp-remote`.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP TanStack Example
Getting Started
To run this application:
pnpm i
pnpm dev
"remote-example": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:3000/api/sse"
]
}
Vercel uses the same Transport as this.
No problems using mcp-remote in Claude:

Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.