Sidvy MCP Server
Provides AI tools with full access to the Sidvy note-taking API, enabling management of notes, todos, groups, and workspaces with search, filtering, and real-time synchronization capabilities.
README
Sidvy MCP Server
A comprehensive MCP (Model Context Protocol) server that provides AI tools with full access to the Sidvy API - a powerful note-taking system with workspaces, groups, todos, and real-time synchronization.
Features
- Full CRUD Operations: Complete access to notes, groups, todos, and workspaces
- Authentication: API key-based authentication for secure access
- Workspace Management: Multi-workspace support with user isolation
- Hierarchical Groups: Organize notes in nested group structures
- Smart Todos: Todo tracking with markdown checkbox synchronization
- Search & Filter: Full-text search across notes and advanced filtering
- Simple Setup: Direct Node.js execution, no complex packaging
- Easy Integration: Works with Claude Desktop, OpenAI ChatGPT, and other MCP-compatible AI tools
Quick Start
1. Get Your API Token
- Go to Sidvy
- Sign up or log in to your account
- Generate an API token from your account settings
- Copy the JWT token
2. Install and Build
# Clone the repository
git clone https://github.com/martinhjartmyr/sidvy-mcp.git
cd sidvy-mcp
# Install dependencies
pnpm install
# Build the server
pnpm run build
3. Set Up Environment
Create a .env file or set environment variables:
SIDVY_API_TOKEN=your_jwt_token_here
SIDVY_API_URL=https://sidvy.com/api
4. Configure Your AI Tool
Claude Desktop Configuration
Add to your claude_desktop_config.json:
{
"mcpServers": {
"sidvy": {
"command": "node",
"args": ["/path/to/sidvy-mcp/build/index.js"],
"env": {
"SIDVY_API_TOKEN": "your_jwt_token_here",
"SIDVY_API_URL": "https://sidvy.com/api"
}
}
}
}
Alternative using absolute path:
{
"mcpServers": {
"sidvy": {
"command": "/path/to/sidvy-mcp/build/index.js",
"env": {
"SIDVY_API_TOKEN": "your_jwt_token_here",
"SIDVY_API_URL": "https://sidvy.com/api"
}
}
}
}
OpenAI ChatGPT Configuration
Add to your MCP configuration:
{
"name": "sidvy",
"command": ["node", "/path/to/sidvy-mcp/build/index.js"],
"env": {
"SIDVY_API_TOKEN": "your_jwt_token_here",
"SIDVY_API_URL": "https://sidvy.com/api"
}
}
Available Tools
Notes Management
list_notes- List notes with filtering and searchcreate_note- Create new markdown notesupdate_note- Edit note content and metadatadelete_note- Move notes to trashsearch_notes- Full-text search across notesget_note- Retrieve specific note by IDget_recent_notes- Get recently updated notesappend_to_note- Add content to existing notes
Groups Management
list_groups- List groups with hierarchical structurecreate_group- Create new groups for organizationupdate_group- Rename or move groupsdelete_group- Remove groups and childrenget_group_tree- Get complete group hierarchyget_root_groups- Get top-level groupsget_child_groups- Get child groups of a parentmove_group- Reorganize group structurecreate_group_path- Create nested group paths
Todos Management
list_todos- List todos with filteringcreate_todo- Create new todosupdate_todo- Edit todo text or statusdelete_todo- Remove todostoggle_todo- Switch completion statuscomplete_todo/uncomplete_todo- Set completion stateget_pending_todos- Get incomplete todosget_completed_todos- Get finished todosget_todos_for_note- Get todos for specific noteget_todo_stats- Get completion statistics
Workspace Management
list_workspaces- List all workspacescreate_workspace- Create new workspace (max 2)update_workspace- Rename workspacesdelete_workspace- Remove workspace and contentget_workspace- Get workspace detailsget_default_workspace- Get user's default workspaceget_workspace_stats- Get content statisticsswitch_workspace- Change active workspace
Example Usage
With Claude Desktop
Once configured, you can ask Claude:
"Create a new note called 'Meeting Notes' with a todo list for today's agenda"
"Search for all notes containing 'project planning' and show me the recent ones"
"Show me all my pending todos across all workspaces"
"Create a group structure for 'Projects/Web Development/Frontend' and add a note there"
Command Line Testing
You can test the server directly:
# Set environment variables
export SIDVY_API_TOKEN="your_token_here"
# Run the built server
node build/index.js
# Or run in development mode
pnpm run dev
# The server will start and wait for MCP protocol messages
Development
Prerequisites
- Node.js 18+
- pnpm
Available Commands
# Install dependencies
pnpm install
# Run in development mode with hot reload
pnpm run dev
# Build for production
pnpm run build
# Run built server
pnpm run start
# Clean build files
pnpm run clean
Configuration Options
Environment Variables
SIDVY_API_TOKEN- Your JWT authentication token (required)SIDVY_API_URL- API base URL (default: https://sidvy.com/api)DEBUG- Enable debug logging (default: false)
API Rate Limits
The Sidvy API has reasonable rate limits for normal usage. The MCP server handles rate limiting gracefully and will retry requests when appropriate.
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
MIT License - see LICENSE file for details.
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.
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.