mcpField
S
Supabase MCP Server on Phala Cloud

Supabase MCP Server on Phala Cloud

Local
github.com/tolakCloud & Infra1Updated 82w ago
Repository

About Supabase MCP Server on Phala Cloud

Supabase MCP Server on Phala Cloud packages the Supabase MCP server for deployment on Phala Cloud. It adds Docker support and SSE transport for remote hosting.

Key features

  1. 01Deploy on Phala Cloud
  2. 02Docker-based deployment
  3. 03SSE transport for remote hosting

Use cases

  1. 01Host the Supabase MCP server remotely
  2. 02Deploy using Phala Cloud's deployment dashboard
  3. 03Run the server locally with Docker Compose

MCP support

It hosts the Supabase MCP server on Phala Cloud and adds SSE transport so MCP clients can connect remotely.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "supabase-mcp-server-tolak": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "build"
      ]
    }
  }
}
Run commanddocker run -i --rm build

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocibuild

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Supabase MCP Server on Phala Cloud

The Supabase MCP Server hosting in TEE on Phala Cloud.

Note the implementation code is fork from supabase, we add docker support make it can be deployed on Phala Cloud. And add transport sse support in ./src/sse.ts to make the server can be hosted remotely.

Deploy on Phala Cloud

To deploy on Phala Cloud, only thing you need to do is copy the ./docker-compose.yml to Phala Cloud deployment dashboard and set environment when deploy it. Head to Phala Cloud doc for more details.

Build locally

  • Build the docker image
docker build --platform linux/amd64 -t <your image name> .
  • Run with docker compose

set environment variable SUPABASE_ACCESS_TOKEN=your_token_here. Then issue command to launch it.

docker compose up
  • Verify your server

Run npx @modelcontextprotocol/inspector (a MCP debug tool) and open its URL in browser. Then connect your server with sse URL "http://localhost:3000/sse".

Comments

Markdown supported

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.