
MCP d'assistance personnelle
Un puissant serveur d'assistant personnel qui s'intègre à divers services, notamment Google Calendar, Obsidian Vault, Trello et les capacités d'analyse de page Web.
3 years
Works with Finder
2
Github Watches
0
Github Forks
2
Github Stars
Personal Assistant MCP Server
A powerful personal assistant server that integrates with various services including Google Calendar, Obsidian Vault, Trello, and web page parsing capabilities. Built using FastMCP, this server provides a unified interface for managing your digital life.
Features
-
Google Calendar Integration
- Create, read, update, and delete calendar events
- List upcoming events
-
Obsidian Vault Management
- Create, read, update, and delete notes
- Full-text search in notes
- Folder management (create, delete, search, list)
-
Trello Integration
- Board, list, and card management
- Create, update, and delete cards
- Search cards by text query
-
Web Page Parsing
- Extract and clean HTML content from any URL
Prerequisites
- Python 3.10 or higher
- Poetry (Python package manager)
- Google Calendar API credentials
- Trello API credentials (if using Trello features)
- Obsidian Vault (if using Obsidian features)
Installation
-
Clone the repository:
git clone https://github.com/yourusername/personal-assistant-mcp.git cd personal-assistant-mcp
-
Install dependencies using Poetry:
poetry install
-
Set up Google Calendar API:
- Go to the Google Cloud Console
- Create a new project or select an existing one
- Enable the Google Calendar API
- Create OAuth 2.0 credentials
- Download the credentials and save them as
credentials.json
in the project root
-
Set up Trello API (optional):
- Go to Trello Developer Portal
- Get your API key and token
- Add them to your environment variables or config file
Configuration
- Run the initial setup to authenticate with Google Calendar:
poetry run python main.py
- This will open a browser window for Google authentication
- Follow the prompts to authorize the application
Usage
-
Start the server:
poetry run python main.py
-
The server will start and be ready to accept MCP-compatible client connections.
-
Use any MCP-compatible client to interact with the server. The server provides the following tools:
- Calendar management
- Obsidian vault operations
- Trello board management
- Web page parsing
Anthropic Claude Desktop Configuration
To use this server with Anthropic Claude Desktop, add the following configuration to your Claude Desktop settings:
{
"mcpServers": {
"personal-assistant": {
"command": "/path/to/your/venv/bin/python",
"args": ["/path/to/your/project/main.py"],
"env": {
"GOOGLE_CREDENTIALS_PATH": "/path/to/your/credentials.json",
"GOOGLE_TOKEN_PATH": "/path/to/your/token.json",
"OBSIDIAN_VAULT_PATH": "/path/to/your/obsidian/vault",
"OBSIDIAN_DEFAULT_FOLDER": "your_default_folder",
"LOG_PATH": "/path/to/log.txt",
"TRELLO_TOKEN": "your_trello_token",
"TRELLO_API_KEY": "your_trello_api_key",
"SEMANTIC_SEARCH_ENABLED": "True/False",
"EMBEDDINGS_PATH": "/path/to/embeddings.json"
}
}
}
}
Replace the paths and credentials with your actual values:
-
command
: Path to your Python virtual environment's Python executable -
args
: Path to your project'smain.py
file -
GOOGLE_CREDENTIALS_PATH
: Path to your Google Calendar credentials file -
GOOGLE_TOKEN_PATH
: Path to your Google Calendar token file -
OBSIDIAN_VAULT_PATH
: Path to your Obsidian vault -
OBSIDIAN_DEFAULT_FOLDER
: Path to default folder in your vault where new notes will be created -
TRELLO_TOKEN
: Your Trello API token -
TRELLO_API_KEY
: Your Trello API key -
SEMANTIC_SEARCH_ENABLED
: Enable semantic search for Obsidian Vault -
EMBEDDINGS_PATH
: Path to embeddings json
To enable semantic search capabilities, you'll need to install the Vector Search plugin for Obsidian.
After the reindexing process is complete, the plugin will generate a JSON file containing vector embeddings at the following location:
.obsidian/plugins/vector-search/data.json
This file will be used as the embedding source for semantic search queries.
Development
- The project uses Poetry for dependency management
- All tools are registered in
main.py
- Service-specific implementations are in the
services/
directory - Follow PEP 8 style guidelines for Python code
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add some amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
Join:
相关推荐
🧑🚀 全世界最好的 LLM 资料总结 (数据处理、模型训练、模型部署、 O1 模型、 MCP 、小语言模型、视觉语言模型) | Résumé des meilleures ressources LLM du monde.
🔥 1Panel fournit une interface Web intuitive et un serveur MCP pour gérer des sites Web, des fichiers, des conteneurs, des bases de données et des LLM sur un serveur Linux.
⛓️RULEGO est un cadre de moteur de règle d'orchestration des composants de nouvelle génération légère, intégrée, intégrée et de nouvelle génération pour GO.
PDF Traduction de papier scientifique avec formats conservés - 基于 AI 完整保留排版的 PDF 文档全文双语翻译 , 支持 Google / Deepl / Olllama / Openai 等服务 , 提供 CLI / GUI / MCP / DOCKER / ZOTERO
Une passerelle basée sur un plugin qui orchestre d'autres MCP et permet aux développeurs de s'appuyer sur des agents de qualité d'entreprise informatiques.
Créez facilement des outils et des agents LLM à l'aide de fonctions Plain Bash / JavaScript / Python.
😎简单易用、🧩丰富生态 - 大模型原生即时通信机器人平台 | 适配 QQ / 微信 (企业微信、个人微信) / 飞书 / 钉钉 / Discord / Telegram / Slack 等平台 | 支持 Chatgpt 、 Deepseek 、 Dify 、 Claude 、 GEMINI 、 XAI 、 PPIO 、 OLLAMA 、 LM Studio 、阿里云百炼、火山方舟、 Siliconflow 、 Qwen 、 Moonshot 、 ChatGlm 、 Sillytraven 、 MCP 等 LLM 的机器人 / Agent | Plateforme de bots de messagerie instantanée basés sur LLM, prend en charge Discord, Telegram, WeChat, Lark, Dingtalk, QQ, Slack