# Fabric MCP Server

An MCP (Model Context Protocol) server that provides access to [Daniel Miessler's Fabric](https://github.com/danielmiessler/fabric) AI patterns. Access 227+ expert-crafted prompts for tasks like extracting wisdom, summarizing content, analyzing arguments, creating visualizations, and much more - all through Claude Desktop!

> **No API keys needed!** Fabric patterns are pure prompts - this MCP server delivers them to Claude, which processes everything natively using its own intelligence. No external AI services, no vendor lock-in, no rate limits.

> **🔄 Auto-Updates!** The server automatically checks for new patterns daily. Always stay current with the latest Fabric patterns!

## 📚 Documentation

- **[QUICKSTART.md](QUICKSTART.md)** - Get started in 5 minutes
- **[AUTO_UPDATE.md](AUTO_UPDATE.md)** - How automatic pattern updates work
- **[PROMPTING_STRATEGIES.md](PROMPTING_STRATEGIES.md)** - How to use patterns effectively
- **[ARCHITECTURE.md](ARCHITECTURE.md)** - How the system works
- **[WHY_NO_CONFIG.md](WHY_NO_CONFIG.md)** - Why zero AI configuration is needed
- **[PROJECT_SUMMARY.md](PROJECT_SUMMARY.md)** - Project overview

## What is Fabric?

Fabric is an open-source framework for augmenting humans using AI. It provides a modular system of expert-crafted prompts (called "patterns") for solving specific problems. Each pattern is a carefully designed system prompt optimized for tasks like:

- **extract_wisdom** - Extract insights, ideas, quotes, and recommendations
- **summarize** - Create concise summaries
- **analyze_claims** - Evaluate arguments and claims
- **create_markmap** - Generate mind map visualizations
- **explain_code** - Explain code in plain language
- **improve_writing** - Enhance written content
- And 100+ more patterns!

## Features

This MCP server brings Fabric patterns to Claude Desktop:

- **Access 227+ Fabric Patterns** - All patterns from the official Fabric repository
- **Pure Prompt Library** - No API keys, no external services, no configuration
- **Apply Patterns to Text** - Use any pattern with your content
- **Browse Patterns** - List and search available patterns
- **Automatic Caching** - Patterns are cached locally for fast access
- **Read Pattern Prompts** - View the full prompt for any pattern
- **Pattern Chaining** - Combine multiple patterns for complex workflows

## Installation

### Prerequisites

- Python 3.10 or higher
- Claude Desktop

### Install from source

1. Clone or download this repository:

```bash
cd "C:\Users\jonat\OneDrive\Coding Projects\fabric-mcp"
```

2. Install dependencies:

```bash
pip install -e .
```

### Configure Claude Desktop

Add the server to your Claude Desktop configuration file:

**Windows**: `%APPDATA%\Claude\claude_desktop_config.json`

**macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`

**Linux**: `~/.config/Claude/claude_desktop_config.json`

Add this configuration:

```json
{
  "mcpServers": {
    "fabric": {
      "command": "python",
      "args": [
        "-m",
        "fabric_mcp.server"
      ]
    }
  }
}
```

Or if you want to use the full path:

```json
{
  "mcpServers": {
    "fabric": {
      "command": "python",
      "args": [
        "C:\\Users\\jonat\\OneDrive\\Coding Projects\\fabric-mcp\\fabric_mcp\\server.py"
      ]
    }
  }
}
```

3. Restart Claude Desktop

## Usage

Once configured, you can use Fabric patterns in Claude Desktop:

### List Available Patterns

```
List all available Fabric patterns
```

or filter by keyword:

```
Show me all Fabric patterns related to "extract"
```

### Apply a Pattern

```
Use the extract_wisdom Fabric pattern on this article: [paste article text]
```

```
Apply the summarize Fabric pattern to this content: [paste content]
```

### View a Pattern

```
Show me the full prompt for the analyze_claims Fabric pattern
```

## Available Tools

The MCP server provides four main tools:

### 1. `apply_fabric_pattern`

Apply any Fabric pattern to input text.

**Parameters:**
- `pattern` - The name of the pattern to apply
- `input_text` - The text content to process

**Example:**
```
Apply the extract_wisdom pattern to analyze this podcast transcript
```

### 2. `list_fabric_patterns`

List all available patterns, optionally filtered by keyword.

**Parameters:**
- `filter` (optional) - Filter patterns by name

**Example:**
```
List all Fabric patterns containing "create"
```

### 3. `get_fabric_pattern`

Get the full prompt/instructions for a specific pattern.

**Parameters:**
- `pattern` - The name of the pattern

**Example:**
```
Show me the full prompt for the improve_writing pattern
```

### 4. `update_fabric_patterns`

Force an immediate update of the pattern list from GitHub (bypasses cache).

**Parameters:**
- None

**Example:**
```
Update my Fabric patterns
```

**Returns:**
- Pattern count changes
- List of new patterns added
- List of patterns removed

## Popular Patterns

Here are some of the most useful Fabric patterns:

- **extract_wisdom** - Extract insights, ideas, quotes, habits, facts, and recommendations
- **summarize** - Create concise summaries
- **explain_code** - Explain code in plain language
- **improve_writing** - Enhance written content
- **create_markmap** - Generate markmap visualizations
- **analyze_claims** - Analyze and evaluate claims
- **extract_article_wisdom** - Extract insights from articles
- **create_quiz** - Generate quiz questions
- **answer_interview_question** - Help with interview prep
- **create_visualization** - Create visual representations
- **rate_content** - Rate content quality
- **check_agreement** - Check if parties agree
- **find_logical_fallacies** - Identify logical fallacies
- **create_stride_threat_model** - Security threat modeling
- **recommend_artists** - Get artist recommendations

And many more! Use `list_fabric_patterns` to see all available patterns.

## How It Works

**This is a pure prompt delivery system - no AI APIs involved!**

1. **Pattern Discovery** - The server fetches the list of available patterns from the Fabric GitHub repository
2. **Pattern Caching** - Patterns are cached locally in `~/.cache/fabric-mcp/` for fast access
3. **Pattern Application** - When you use a pattern, it combines the pattern prompt with your input text
4. **Claude Processing** - Claude receives the complete prompt and processes your content natively

**Architecture:**
```
You → Claude Desktop → MCP Server → Fabric Pattern (prompt)
                    ↓
              Claude's LLM (processes everything locally)
                    ↓
                 Result
```

No external API calls, no vendor configuration, no rate limits!

## Resources

Each Fabric pattern is also available as an MCP resource with the URI format:

```
fabric://pattern/{pattern_name}
```

For example:
- `fabric://pattern/extract_wisdom`
- `fabric://pattern/summarize`
- `fabric://pattern/analyze_claims`

## Prompting Strategies

Fabric patterns are expert-crafted prompts that encode best practices. Learn how to use them effectively:

### Pattern Chaining
Combine multiple patterns for complex workflows:
```
1. extract_wisdom → Get insights
2. summarize → Condense insights
3. create_quiz → Test knowledge
```

### Pattern Customization
Adapt patterns on-the-fly:
```
Use extract_wisdom but focus only on technical insights
and extract 10 ideas instead of 25
```

### Multi-Pattern Analysis
Apply different perspectives:
```
Analyze this article with:
- extract_wisdom (insights)
- analyze_claims (arguments)
- rate_content (quality)
```

**📚 For comprehensive prompting strategies, see [PROMPTING_STRATEGIES.md](PROMPTING_STRATEGIES.md)**

This includes:
- Pattern selection guidelines
- Chaining workflows
- Best practices
- Common patterns by use case
- Advanced techniques

## Troubleshooting

### Patterns not loading

The server will try to load patterns from GitHub. If you're offline or experiencing issues:

1. Check your internet connection
2. The server caches patterns in `~/.cache/fabric-mcp/`
3. Check Claude Desktop logs for errors

### Server not appearing in Claude

1. Verify your `claude_desktop_config.json` is valid JSON
2. Check that the Python path is correct
3. Restart Claude Desktop completely
4. Check Claude Desktop logs:
   - Windows: `%APPDATA%\Claude\logs`
   - macOS: `~/Library/Logs/Claude`
   - Linux: `~/.config/Claude/logs`

## Credits

- **Fabric Framework** by [Daniel Miessler](https://github.com/danielmiessler)
- All patterns are from the [Fabric repository](https://github.com/danielmiessler/fabric)
- Built with [Model Context Protocol](https://modelcontextprotocol.io)

## License

MIT License - See LICENSE file for details

The Fabric patterns themselves are from the Fabric project and maintain their original MIT license.

## Contributing

Contributions welcome! This is a simple MCP wrapper around the Fabric patterns. To contribute:

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Submit a pull request

## Support

For issues with:
- **This MCP Server** - Open an issue in this repository
- **Fabric Patterns** - See the [Fabric repository](https://github.com/danielmiessler/fabric)
- **MCP Protocol** - See the [MCP documentation](https://modelcontextprotocol.io)

---

**Enjoy using Fabric patterns with Claude Desktop!** 🎨✨