Metadata-Version: 2.4
Name: revibe-mcp
Version: 0.1.0
Summary: MCP server for Revibe codebase analysis — works with Claude Desktop, Cursor, Windsurf, and any MCP-compatible client
Project-URL: Homepage, https://revibe.codes
Project-URL: Repository, https://github.com/selvatuple/revibe-mcp
Project-URL: Documentation, https://revibe.codes
Author-email: Revibe <hello@revibe.codes>
License-Expression: MIT
Keywords: ai-agent,architecture,claude,code-analysis,cursor,mcp,revibe,windsurf
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Documentation
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.10
Requires-Dist: httpx>=0.27.0
Requires-Dist: mcp[cli]>=1.0.0
Description-Content-Type: text/markdown

# Revibe MCP Server

MCP (Model Context Protocol) server for [Revibe](https://revibe.codes) codebase analysis. Works with Claude Desktop, Cursor, Windsurf, and any MCP-compatible client.

## Setup

### 1. Install

```bash
pip install revibe-mcp
```

### 2. Log in

```bash
revibe-mcp-auth login
```

This opens your browser — sign up or log in, click "Authorize", and you're done. The API key is saved automatically to `~/.config/revibe/credentials.json`.

### 3. Configure your MCP client

Add the server to your MCP client config. No API key needed in the config — it's loaded from saved credentials automatically.

#### Claude Desktop

Add to `~/Library/Application Support/Claude/claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "revibe": {
      "command": "revibe-mcp"
    }
  }
}
```

#### Claude Code

Add to your project's `.mcp.json`:

```json
{
  "mcpServers": {
    "revibe": {
      "command": "revibe-mcp"
    }
  }
}
```

#### Cursor

Go to **Settings > MCP Servers > Add**, then set command to `revibe-mcp`.

#### Windsurf

Add to your Windsurf MCP config:

```json
{
  "mcpServers": {
    "revibe": {
      "command": "revibe-mcp"
    }
  }
}
```

Alternatively, you can pass the API key directly via environment variable:

```json
{
  "mcpServers": {
    "revibe": {
      "command": "revibe-mcp",
      "env": {
        "REVIBE_API_KEY": "rk_live_your_key_here"
      }
    }
  }
}
```

## Tools

| Tool | Description |
|------|-------------|
| `revibe_login` | Log in via browser (also works as an MCP tool from inside your AI assistant). |
| `analyze_repo` | Submit a GitHub repo for analysis. Auto-detects from git remote if no URL given. |
| `check_status` | Check progress of an analysis job. |
| `get_summary` | Get a condensed summary — architecture, modules, patterns. |
| `get_section` | Drill into a specific section (architecture, file_roles, system_design_qa, etc.). |
| `get_agent_context` | Get the full structured agent context JSON — optimized for AI consumption. |

## CLI Commands

```bash
revibe-mcp-auth login    # Log in via browser
revibe-mcp-auth status   # Show current auth status
revibe-mcp-auth logout   # Remove saved credentials
```

## Usage

Once configured, just ask your AI assistant:

- "Analyze this repo with Revibe"
- "What's the architecture of github.com/user/repo?"
- "Get the agent context for this codebase"

The tools handle auto-detection, polling, and structured output automatically.
