worklab-tools — MCP Server for Personal Knowledge Management

A Model Context Protocol (MCP) server that provides AI-powered tools for knowledge management, including semantic search, audio transcription, image generation, and PPT creation.

Built for use with Claude Code and the Knowledge system.

Tools

| Tool | Description | |------|-------------| | search_knowledge(query, type?, company?, person?) | Semantic search over knowledge base (ChromaDB + bge-m3) | | index_knowledge() | Full rebuild of vector index from all markdown files | | upsert_knowledge() | Incremental index update (MD5 diff, only re-index changed files) | | generate_ppt(topic, context_text?, page_count?) | Generate PPT: plan outline → slide images → PDF output | | generate_image(prompt, filename?) | Generate image from text description (Gemini) | | transcribe_audio(file_path, model_size?) | Speech-to-text with speaker diarization (Whisper + pyannote) | | register_voiceprint(name, file_path) | Register speaker voiceprint for future identification |

Setup

# Clone
git clone https://github.com/Ryeliu/worklab-tools.git
cd worklab-tools

# Install dependencies (requires Python 3.12+, uv recommended)
uv sync

# Configure environment
cp .env.example .env
# Edit .env with your API keys

# Run
uv run mcp run server.py

Environment Variables

Create a .env file:

GEMINI_API_KEY=your_google_ai_studio_key
HF_TOKEN=your_huggingface_token
OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
OPENROUTER_API_KEY=your_openrouter_key

| Variable | Required For | Source | |----------|-------------|--------| | GEMINI_API_KEY | generate_image | Google AI Studio | | HF_TOKEN | transcribe_audio, register_voiceprint | HuggingFace | | OPENROUTER_API_KEY | generate_ppt | OpenRouter |

Register with Claude Code

Add to your Claude Code MCP settings:

{
  "mcpServers": {
    "worklab-tools": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/worklab-tools", "mcp", "run", "server.py"],
      "env": {
        "GEMINI_API_KEY": "...",
        "HF_TOKEN": "...",
        "OPENROUTER_BASE_URL": "https://openrouter.ai/api/v1",
        "OPENROUTER_API_KEY": "..."
      }
    }
  }
}

Dependencies

Semantic Search: chromadb, sentence-transformers (BAAI/bge-m3, CPU)
Transcription: openai-whisper (large-v3), pyannote.audio (speaker diarization)
PPT Generation: openai SDK (OpenRouter → Gemini), Pillow
Image Generation: httpx (Gemini API direct)

License

MIT

worklab-tools