Evernote MCP Server
A Model Context Protocol server that allows AI assistants like Claude to interact with Evernote, enabling them to create, search, read, and manage notes through natural language.
README
๐ Evernote MCP Server
A Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with Evernote, allowing them to create, search, read, and manage notes seamlessly through natural language.
๐ค Transform your Evernote into Claude's brain! This MCP server bridges the gap between AI and your personal knowledge base.
โจ Features
๐ง AI Tools Available
search_notes- Search through your Evernote notes with advanced queriesget_note_content- Retrieve full content of specific notescreate_note- Create new notes with title, content, and tagsupdate_note- Modify existing notescreate_notebook- Create new notebooks for organizationconfigure_evernote- Set up authentication with your Evernote account
๐ Live Resources
notebooks://list- Real-time access to your notebook structuretags://list- Available tags for organizationrecent-notes://list- Recently modified notes
๐ Quick Installation
Prerequisites
- Python 3.8+ (if not installed, see Python Installation Guide below)
- Git (for cloning the repository)
Option 1: One-Click Install (Recommended)
# Clone this repository
git clone https://github.com/Ak-9647/Evernote-MCP.git
cd Evernote-MCP
# Run the automated setup
python setup.py
Option 2: Manual Setup
# Clone the repository
git clone https://github.com/Ak-9647/Evernote-MCP.git
cd Evernote-MCP
# Install dependencies
pip install -r requirements.txt
Python Installation
If you don't have Python installed:
Windows:
- Download Python from python.org
- IMPORTANT: Check "Add Python to PATH" during installation
- Restart your terminal/PowerShell after installation
- Test:
python --version
macOS:
# Using Homebrew (recommended)
brew install python
# Or download from python.org
Linux:
# Ubuntu/Debian
sudo apt update && sudo apt install python3 python3-pip
# CentOS/RHEL
sudo yum install python3 python3-pip
๐ Get Your Evernote API Key
IMPORTANT: You need an Evernote Developer Token to use this MCP server.
Step-by-Step Guide:
-
Request API Access by filling out their contact form:
Full Name: [Your Name] Organization: Personal Use Application Name: Personal MCP Server Description: MCP server for AI assistant integration with personal Evernote account Access Level: Full Access (recommended) or Basic Access -
Wait for Approval (usually 1-5 business days)
-
You'll receive via email:
- Consumer Key
- Consumer Secret
- Developer Token โ This is what you need!
โ๏ธ Configuration with Claude Desktop
Step 1: Locate Claude Desktop Config File
Find 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
Step 2: Add MCP Server Configuration
Add this to your claude_desktop_config.json file:
{
"mcpServers": {
"evernote": {
"command": "python",
"args": ["/full/path/to/Evernote-MCP/evernote_mcp_server.py"],
"env": {}
}
}
}
Replace /full/path/to/Evernote-MCP/ with the actual path where you cloned this repository!
Step 3: Restart Claude Desktop
Close and reopen Claude Desktop to load the new MCP server.
๐ Setting Up Your API Key
Method 1: Through Claude (Recommended)
- Open Claude Desktop
- Say: "Configure Evernote with my developer token: YOUR_DEVELOPER_TOKEN_HERE"
- Claude will respond with confirmation that Evernote is configured
Method 2: Environment Variables (Advanced)
Create a .env file in the project directory:
# .env file
EVERNOTE_DEVELOPER_TOKEN=your_token_here
EVERNOTE_USE_SANDBOX=true
๐จ Security Note: Never commit your actual API tokens to Git! The .env file is already in .gitignore.
๐ก How to Use with Claude
Once configured, you can interact with your Evernote through natural language in Claude:
๐ Creating Notes
๐ค "Create a note called 'Meeting Summary' with today's discussion points and tag it 'work'"
๐ค Claude will create the note and confirm: "I've created a note titled 'Meeting Summary'
in your default notebook with the 'work' tag."
๐ Searching Notes
๐ค "Find all my notes about machine learning from the past month"
๐ค Claude will search and show: "I found 5 notes about machine learning from the past month:
1. 'Neural Networks Basics' (Dec 15)
2. 'TensorFlow Tutorial' (Dec 20)..."
๐ Reading Content
๐ค "Show me the content of my note titled 'Project Ideas'"
๐ค Claude will retrieve and display the full note content with formatting preserved.
๐๏ธ Organization
๐ค "Create a new notebook called 'AI Research' and organize my machine learning notes there"
๐ค Claude will create the notebook and can help move related notes.
๐ Smart Updates
๐ค "Add today's meeting notes to my existing 'Weekly Standup' note"
๐ค Claude will find the note and append the new information.
๐งช Testing Your Installation
Quick Test
Run the built-in test script:
cd Evernote-MCP
python test_server.py
Pre-flight Check:
# Verify Python is working
python --version
# Check dependencies
python -c "import httpx; print('โ
httpx available')"
# Test MCP server loads
python -c "from evernote_mcp_server import app; print('โ
MCP server loads successfully')"
This will test:
- โ Python dependencies
- โ MCP server functionality
- โ Claude Desktop configuration
- โ Evernote API connection (if you provide your token)
Automated Testing (for CI/CD)
The test script can be run non-interactively, perfect for automated workflows:
python test_server.py --non-interactive --token "YOUR_EVERNOTE_TOKEN"
The script will exit with a non-zero status code if any tests fail.
Manual Verification
- Check Claude Desktop - Look for "๐ง Evernote" in Claude's available tools
- Test Configuration - Say: "Configure Evernote with my token: YOUR_TOKEN"
- Test Search - Say: "Search my Evernote for any note"
๐ง Architecture
โโโโโโโโโโโโโโโโโโโ MCP Protocol โโโโโโโโโโโโโโโโโโโ Evernote API โโโโโโโโโโโโโโโโโโโ
โ โโโโโโโโโโโโโโโโโโโโโบโ โโโโโโโโโโโโโโโโโโโโโบโ โ
โ Claude Desktop โ (JSON-RPC) โ Evernote MCP โ (HTTPS) โ Evernote โ
โ (MCP Client) โ โ Server โ โ Service โ
โ โ โ โ โ โ
โโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโ
Component Breakdown:
- Claude Desktop - The MCP client that sends requests
- Evernote MCP Server - This application that translates MCP calls to Evernote API
- Evernote Service - The actual Evernote cloud service
๐ Security & Authentication
Developer Tokens
- Used for development and personal use
- Tied to a specific Evernote account
- Access level determined when requesting API key
OAuth (Future Enhancement)
- For production applications
- Allows users to authorize access without sharing credentials
- More secure for shared or distributed applications
Environment Variables
For enhanced security, you can set environment variables:
export EVERNOTE_DEVELOPER_TOKEN="your_token_here"
export EVERNOTE_USE_SANDBOX="true" # Set to "false" for production
๐ ๏ธ Development
Project Structure
evernote-mcp-server/
โโโ evernote_mcp_server.py # Main MCP server implementation
โโโ requirements.txt # Python dependencies
โโโ README.md # This file
โโโ tests/ # Unit tests (future)
Key Classes
EvernoteClient- Handles Evernote API communicationFastMCP- The MCP server framework- Tools & Resources - MCP endpoints for AI interaction
Testing
# Install test dependencies
pip install pytest pytest-asyncio
# Run tests (when implemented)
pytest tests/
๐ Troubleshooting
โ "Evernote client not initialized"
Solution:
- Run: "Configure Evernote with my developer token: YOUR_TOKEN" in Claude
- Verify your developer token is correct
- Check if you're using sandbox vs production environment
โ Claude doesn't see the Evernote tools
Solution:
- Restart Claude Desktop completely
- Check the path in
claude_desktop_config.jsonis correct - Ensure Python can run:
python evernote_mcp_server.py
โ "Failed to create note"
Solution:
- Ensure your API key has create permissions (Full Access recommended)
- Check that the specified notebook exists
- Verify your token hasn't expired
โ Connection/Authentication Issues
Solution:
- Test your token:
python test_server.py - Confirm internet connectivity
- Check if corporate firewall blocks Evernote API
- Try sandbox environment first:
EVERNOTE_USE_SANDBOX=true
โ Import/Module Errors
Solution:
# Reinstall dependencies
pip install --upgrade -r requirements.txt
# Check Python version
python --version # Should be 3.8+
๐ก Still Having Issues?
- Run the test script:
python test_server.py - Check the logs in Claude Desktop's developer console
- Create an issue on this GitHub repository with:
- Your operating system
- Python version
- Error messages
- Steps you've tried
๐ฆ API Limits
Evernote has rate limits on API usage:
- Basic Access: Limited operations per hour
- Full Access: Higher rate limits
- Production: Different limits than sandbox
The server includes error handling for rate limit responses.
๐ Installing from GitHub (For Users)
If someone shared this repository with you, here's how to get it running:
Quick Setup Commands
# Clone the repository
git clone https://github.com/Ak-9647/Evernote-MCP.git
cd Evernote-MCP
# Install and configure everything
python setup.py
# Test your installation
python test_server.py
What the setup does:
- โ Installs all Python dependencies
- โ Configures Claude Desktop automatically
- โ Guides you through getting your Evernote API key
- โ Tests everything works correctly
๐ฃ๏ธ Roadmap
- [ ] OAuth Support - More secure authentication
- [ ] Web Clipper Integration - Save web pages via Claude
- [ ] Shared Notebooks - Collaborate through AI
- [ ] Advanced Search - Saved searches and filters
- [ ] File Attachments - Handle images and documents
- [ ] Multi-Account - Support multiple Evernote accounts
๐ค Contributing
We welcome contributions! Here's how:
For Developers:
- Fork this repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Commit your changes:
git commit -m 'Add amazing feature' - Push to the branch:
git push origin feature/amazing-feature - Open a Pull Request
For Users:
- ๐ Report bugs via GitHub Issues
- ๐ก Suggest features you'd like to see
- ๐ Improve documentation
- โญ Star this repo if you find it useful!
๐ Project Stats
๐ License
This project is licensed under the MIT License - see the LICENSE file for details.
๐ Related Projects & Links
- ๐ Model Context Protocol Documentation
- ๐ Evernote Developer Documentation
- ๐ Claude Desktop
- ๐ MCP Server Registry
โ ๏ธ Important Disclaimers
- Unofficial Project: Not affiliated with or endorsed by Evernote Corporation
- Security: Keep your API tokens secure and never commit them to public repositories
- Compliance: Ensure you follow Evernote's Terms of Service and API License Agreement
- Rate Limits: Respect Evernote's API rate limits to avoid service interruption
๐ Success Stories
"This MCP server transformed how I use my Evernote. Now Claude can help me organize 10 years of notes effortlessly!" - Happy User
Made with โค๏ธ for the AI community
Star โญ this repo if it helps you! Happy Note-Taking with AI! ๐ค๐
๐ ๏ธ Developer Mode
For advanced users and developers, a Developer Mode can be enabled to access extra debugging tools and verbose logging.
How to Enable:
Set the DEV_MODE environment variable to true. This can be done in your claude_desktop_config.json or directly in your shell.
Example claude_desktop_config.json:
{
"mcpServers": {
"evernote": {
"command": "python",
"args": ["/full/path/to/Evernote-MCP/evernote_mcp_server.py"],
"env": {
"DEV_MODE": "true"
}
}
}
}
Developer Features
- ๐ Verbose Logging: See detailed API requests and responses (including payloads) in the server console.
- ๐ก๏ธ Dry Run Mode: Add
dry_run=Truetocreate_noteorupdate_notetool calls to simulate the action without modifying your data. This is great for testing prompts. - ๐ง New Dev Tools:
dev_get_config: Returns the current server configuration (token status, environment, etc.).dev_clear_config: Resets the Evernote authentication, useful for switching accounts.dev_api_test: Performs a live API test to check connectivity and permissions.
๐งช Testing Your Installation
Quick Test
Run the built-in test script:
cd Evernote-MCP
python test_server.py
This will test:
- โ Python dependencies
- โ MCP server functionality
- โ Claude Desktop configuration
- โ Evernote API connection (if you provide your token)
Automated Testing (for CI/CD)
The test script can be run non-interactively, perfect for automated workflows:
python test_server.py --non-interactive --token "YOUR_EVERNOTE_TOKEN"
The script will exit with a non-zero status code if any tests fail.
Manual Verification
- Check Claude Desktop - Look for "๐ง Evernote" in Claude's available tools
- Test Configuration - Say: "Configure Evernote with my token: YOUR_TOKEN"
- Test Search - Say: "Search my Evernote for any note"
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.