# Corge MCP server

> Provides a unified TypeScript SDK for managing authentication, databases, storage, payments, and multimodal AI within a single declarative API.

- Repository: https://github.com/corgelabs/corge
- Page: https://hostedmcp.org/servers/corgelabs/corge
- Transport: stdio
- Stars: 0

## Install

### Claude Code

```sh
claude mcp add corge -- npx -y @corgelabs/corge
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "corge": {
      "command": "npx",
      "args": [
        "-y",
        "@corgelabs/corge"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "corge": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@corgelabs/corge"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"corge","type":"stdio","command":"npx","args":["-y","@corgelabs/corge"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "corge": {
      "command": "npx",
      "args": [
        "-y",
        "@corgelabs/corge"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add corge -- npx -y @corgelabs/corge
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.corge]
command = "npx"
args = ["-y", "@corgelabs/corge"]
```

### Gemini CLI

```sh
gemini mcp add -s user corge npx -- -y @corgelabs/corge
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "corge": {
      "command": "npx",
      "args": [
        "-y",
        "@corgelabs/corge"
      ]
    }
  }
}
```

## FAQ

### What does Corge replace?

It replaces the need for multiple separate SDKs by collapsing the entire SaaS and AI stack—including auth, DB, storage, and payments—into one API.

### How do I set up Corge for an AI agent?

You can add specific backend rules to your repository's AGENTS.md or CLAUDE.md files, instructing the agent to read the specification file before writing code.

### Can I deploy Corge to the cloud?

Yes, the Corge CLI includes a deploy command that bundles your code and deploys it to GCP Cloud Functions v2.

### Does it support durable workflows?

Yes, it supports durable workflows with Saga rollback capabilities using a step-based approach.
