autogenstudio-skills - GitLite

KO | EN

gitlite — search

#python #react #typescript #llm #go #machine-learning #rust #deep-learning #java #windows #awesome #kubernetes #security #mcp

autogenstudio-skills

(★ 317)

Repo of skills for autogen studio using model context protocol (mcp)

파일 탐색기

최종 버전 다운로드 (.zip)

- CODEOWNERS
- mcp_gallery.json
- - moved.txt
  - test.txt
- - moved.txt
- .gitkeep
- greetings.txt
- generate_mcp_json.py
- mcp_tool_tester_team.json
- multiagent_team.json
- test_mcp_client.py
- test_mcp_json.py
- mcp.json
- mcp_client.py
- - fetch_post.py
  - README.md
- - document_indexer.py
  - document_retriever.py
  - README.md
- - README.md
  - slack_search.py
- - README.md
  - stackoverflow_teams.py
- - README.md
  - story_mode.py
- - plot_diagram.py
  - webscrape.py
- - duck_duck_go.py
  - README.MD
  - web_search.py
.gitignore
LICENSE
mcp_config.example.json
README.md
requirements.txt
setup.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/madtank/autogenstudio-skills

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd autogenstudio-skills

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. 공식 설치 스크립트

쉬움 추천

사전 준비물

Python 3 pip 명령어를 쓰려면 Python이 필요합니다.

pip install mcp

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

✅ 설치 후 새 터미널을 열고, 프로그램의 버전 확인 명령(예: --version)으로 정상 설치됐는지 확인하세요.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

3. Python

쉬움

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

python -m venv .env

파이썬 스크립트(또는 모듈)를 실행합니다.

pip install mcp

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# AutoGen Studio MCP Tools

## What is MCP?

Model Context Protocol (MCP) is like a USB for AI tools - it provides a standardized way for AI agents to discover and use different capabilities. Think of it as plugging in new abilities for your AI agents! With our flexible dictionary-based implementation, agents can easily discover and use tools without needing to know their implementation details.

### Available MCP Servers

The MCP ecosystem is growing rapidly with many powerful servers available:

- **Brave Search** - Web and local search capabilities
- **Filesystem** - Complete file and directory operations
- **Playwright** - Browser automation and web scraping
- **MongoDB** - Direct database interactions
- **Sequential Thinking** - Structured reasoning and planning
- **FLUX** - Image generation and manipulation
- **Selenium** - Web automation and testing
- **SQLite** - Local database operations
- **Vector Store** - Embedding and similarity search
- **And many more!**

Check out the [MCP Servers Repository](https://github.com/modelcontextprotocol/servers) for the latest list of available servers. The ecosystem is rapidly growing with new capabilities being added regularly!

## Quick Start

1. **Install Requirements**:
```bash
# Create and activate virtual environment
python -m venv .env
source .env/bin/activate  # On Windows: .env\Scripts\activate

# Install required packages
pip install mcp
```

2. **Configure MCP**:
```bash
# Copy the example config
cp mcp_config.example.json mcp_config.json

# Edit mcp_config.json with your settings
{
  "mcpServers": {
    "brave-search": {
      "enabled": true,
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-brave-search"],
      "env": {
        "BRAVE_API_KEY": "your-api-key-here"
      }
    },
    "filesystem": {
      "enabled": true,
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/your/working/directory"
      ]
    }
  }
}
```

3. **Start AutoGen Studio**:
```bash
autogenstudio ui --port 8080
```

## Dynamic Tool Usage

Our implementation uses a flexible dictionary-based approach, making it easy to discover and use tools:

```python
# 1. List Available Servers
servers = await mcp(tool='list_available_servers')

# 2. Discover Server Tools
tools = await mcp(
    server='brave-search',
    tool='tool_details'
)

# 3. Use Tools with Dictionary Arguments
# Web Search Example
result = await mcp(
    server='brave-search',
    tool='brave_web_search',
    arguments={
        'query': 'Latest AI developments',
        'count': 5
    }
)

# File Operations Example
result = await mcp(
    server='filesystem',
    tool='read_file',
    arguments={
        'path': '/path/to/your/file'
    }
)
```

## Example Templates

We provide ready-to-use templates to help you get started:

1. **Gallery Examples** (`/gallerys`):
   - Pre-configured tool setups
   - Example implementations
   - Best practices demonstrations

2. **Team Templates** (`/teams`):
   - Complete agent workflows
   - Tool integration examples
   - Task-specific configurations

To use a template:
1. Copy the desired template from `/gallerys` or `/teams`
2. Customize the JSON configuration for your needs
3. Load it in AutoGen Studio

## Available Tools

### 1. Brave Search
- Web search capabilities
- Local business search
- Configurable result limits
- Fresh content filtering

### 2. File Operations
- Read/Write files
- Directory operations
- File searches
- Metadata operations

### 3. More Coming Soon
The MCP ecosystem is constantly growing. Add new servers to your config to expand capabilities!

## Configuration Locations

The MCP client checks these locations for config files:

1. Current directory: `./mcp_config.json`
2. User config: `~/.config/autogen/mcp_config.json`
3. Environment: `$MCP_CONFIG_PATH`

## Development

### Testing
Run the test suite:
```bash
pytest tests/test_mcp_client.py -v
pytest tests/test_mcp_json.py -v
```

### Workspace
The `/mcp_workspace` directory is provided for testing but ignored by git. Your tests will create this automatically.

## Requirements

- Python 3.12+
- Node.js and npx
- MCP Python SDK
- AutoGen Studio

## License

MIT License - See LICENSE file for details