Notes MCP Server
Enables creating, managing, and searching Markdown notes with support for tags, timestamps, and full-text search. Includes AI prompts for analyzing and summarizing notes.
README
📝 Notes MCP Server
A Model Context Protocol (MCP) server for managing notes in Markdown format. Built with Python and the FastMCP SDK.
🌟 Features
- Create Notes: Create new Markdown notes with titles, content, and tags
- List & Filter: View all notes or filter by specific tags
- Search: Full-text search across all notes with context preview
- Update: Append content to existing notes with timestamps
- Delete: Remove notes when no longer needed
- Resources: Access all notes as a single MCP resource
- AI Prompts: Built-in prompt for analyzing and summarizing notes
📦 Installation
Prerequisites
- Python 3.10 or higher
- uv package manager
Install uv
# MacOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
# Or via pip
pip install uv
Install Dependencies
# Using uv (recommended)
uv pip install mcp
# Or using pip
pip install mcp
🚀 Quick Start
1. Save the Server
Save notes_server.py in your desired directory.
2. Run the Server
# Using uv (recommended)
uv run notes_server.py
# Or using python directly
python notes_server.py
3. Configure in Claude Desktop
Add to your claude_desktop_config.json:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"notes": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/notes-mcp-server",
"run",
"notes_server.py"
]
}
}
}
Alternative with Python:
{
"mcpServers": {
"notes": {
"command": "python",
"args": ["/absolute/path/to/notes_server.py"]
}
}
}
4. Restart Claude Desktop
After adding the configuration, restart Claude Desktop to load the MCP server.
🛠️ Available Tools
create_note
Create a new note with title, content, and optional tags.
Parameters:
title(string): Note titlecontent(string): Note content in Markdowntags(string, optional): Comma-separated tags
Example:
Create a note titled "Project Ideas" with content "1. Build MCP server\n2. Add search" and tags "work, ideas"
list_notes
List all notes with their titles and creation dates.
Parameters:
tag(string, optional): Filter by specific tag
Example:
List all notes
List notes with tag "work"
read_note
Read the full content of a specific note.
Parameters:
filename(string): The filename of the note (e.g.,20241106_120000_project_ideas.md)
Example:
Read note "20241106_120000_project_ideas.md"
search_notes
Search for notes containing specific text.
Parameters:
query(string): Search query
Example:
Search notes for "Python"
update_note
Append content to an existing note with timestamp.
Parameters:
filename(string): The filename of the notecontent(string): Content to append
Example:
Update note "20241106_120000_project_ideas.md" with "3. Implement testing"
delete_note
Delete a note permanently.
Parameters:
filename(string): The filename of the note
Example:
Delete note "20241106_120000_old_note.md"
📚 Resources
notes://all
Access all notes as a combined resource. Useful for context-aware operations.
💡 Prompts
summarize_notes_prompt
Generates a prompt for AI to analyze all notes and provide:
- Summary of main themes
- Recurring ideas or patterns
- Important action items
- Recommendations for organization
📁 File Structure
Notes are stored in the notes/ directory with the following format:
notes/
├── 20241106_120000_project_ideas.md
├── 20241106_130000_shopping_list.md
└── 20241106_140000_python_notes.md
Note Format
Each note is a Markdown file with metadata:
# Project Ideas
**Created:** 2024-11-06 12:00:00
**Tags:** work, ideas
---
1. Build MCP server
2. Add search functionality
3. Implement testing
🧪 Testing
A test script is included to verify functionality without connecting to an LLM:
python test_notes_server.py
The test script will:
- Create sample notes
- List and filter notes
- Search for content
- Update and delete notes
- Test all features
🔧 Configuration
Notes Directory
By default, notes are stored in ./notes/. To change the location, modify the NOTES_DIR variable in notes_server.py:
NOTES_DIR = os.path.join(os.path.dirname(__file__), "notes")
Filename Generation
Notes are saved with timestamps and sanitized titles:
- Format:
YYYYMMDD_HHMMSS_sanitized_title.md - Max title length: 100 characters
- Special characters are removed
- Spaces converted to underscores
📝 Usage Examples
Create a Note
"Create a note titled 'Meeting Notes' with content 'Discussed Q4 goals' and tags 'work, meetings'"
Find Related Notes
"Search my notes for anything related to 'Python'"
Review Notes by Category
"List all notes tagged with 'personal'"
Summarize Notes
"Use the summarize_notes_prompt to analyze all my notes"
🤝 Contributing
Contributions are welcome! Feel free to:
- Report bugs
- Suggest new features
- Submit pull requests
📄 License
This project is open source and available under the MIT License.
🔗 Resources
⚠️ Limitations
- Text-based notes only (no file attachments)
- No note encryption
- Single notes directory (no subdirectories)
- UTF-8 encoding only
💬 Support
For issues or questions:
- Check the test script output for debugging
- Review the notes directory permissions
- Ensure Python 3.10+ is installed
- Verify MCP SDK installation
Made with ❤️ using FastMCP
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.