Fastidious MCP Server
Enables to manage notes and collections in Fastidious AI application through natural language, supporting CRUD operations and search via MCP protocol.
README
Fastidious MCP Server
MCP (Model Context Protocol) server for Fastidious AI notes application.
Deployment
Environment Variables
| Variable | Description | Default |
|---|---|---|
FASTIDIOUS_URL |
Fastidious API base URL | http://localhost:3000 |
Deploy to Coolify
- Create a new service in Coolify
- Connect to this repository
- Set build pack to Nixpacks or Dockerfile
- Configure environment variable:
Or for internal Docker network:FASTIDIOUS_URL=https://blog.tjb.appFASTIDIOUS_URL=http://fastidious:3000 - Set the domain to
mcp.tjb.app - Deploy
Docker
docker build -t fastidious-mcp .
docker run -p 3001:3001 -e FASTIDIOUS_URL=https://blog.tjb.app fastidious-mcp
Usage
Claude Desktop Configuration
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"fastidious": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.tjb.app/sse?token=YOUR_TOKEN_HERE"]
}
}
}
Get your token from Fastidious AI Settings (sidebar → profile → Settings).
Note: Uses mcp-remote to proxy the remote SSE connection.
Local Development (stdio mode)
For local testing with Claude Desktop:
{
"mcpServers": {
"fastidious": {
"command": "npx",
"args": ["tsx", "/path/to/mcp-server/src/index.ts"],
"env": {
"FASTIDIOUS_TOKEN": "YOUR_TOKEN_HERE",
"FASTIDIOUS_URL": "https://blog.tjb.app"
}
}
}
}
Available Tools
| Tool | Description |
|---|---|
create_note |
Create a new markdown note |
get_note |
Get a note by ID |
update_note |
Update a note |
delete_note |
Delete a note |
list_notes |
List all notes (with optional collection filter) |
search_notes |
Search notes by content |
create_collection |
Create a new collection |
get_collection |
Get a collection (with optional contents) |
list_collections |
List all collections |
add_to_collection |
Add notes to a collection |
remove_from_collection |
Remove notes from a collection |
Architecture
Claude Desktop
↓ MCP Protocol (SSE)
MCP HTTP Server (mcp.tjb.app)
↓ HTTP + Bearer Token
Fastidious API (blog.tjb.app/api/mcp/*)
↓
User's Notes & Collections
API Endpoints
GET /health- Health checkGET /sse?token=TOKEN- MCP SSE endpoint for Claude Desktop
Internal Network (Docker/Coolify)
If running alongside Fastidious in the same Docker network:
FASTIDIOUS_URL=http://fastidious:3000
This avoids external network hops for better performance.
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.