Noteit MCP
An HTTP MCP server that allows AI coding tools to manage agent profiles and take structured notes with visual diagrams, supporting 60+ expert personas for specification-driven development.
README
<p align="center"> <img src="assets/log.png" alt="Noteit MCP" width="180" /> </p>
Noteit MCP
🩹 The cure for AI "Markdown Hell" - AI prompt library + visual knowledge hub for developers
Noteit-MCP transforms drowning in 5,000-word documents into navigable HTML and logic diagrams instantly. With 60+ expert personas, organize complex ideas without cognitive overload. Makes Specification-Driven Development actually human-readable.
✨ Demo & Screenshots
🎥 Noteit MCP in Action - Complete usage walkthrough
<p align="center"> <a href="https://www.youtube.com/watch?v=-cRqrBOzKIc&t=24s"> <img src="https://img.youtube.com/vi/-cRqrBOzKIc/0.jpg" alt="Noteit MCP Demo Video" width="800" /> </a> <br /> <em>🎬 Click to watch the complete demo</em> </p>
<p align="center"> <img src="assets/demo/noteweb.png" alt="Noteit Dashboard" width="800" /> <br /> <em>📊 Unified dashboard with agent profiles and note management</em> </p>
<p align="center"> <img src="assets/demo/noteweb2.png" alt="Agent Profiles" width="800" /> <br /> <em>🤖 40+ pre-built agent templates for different coding tasks</em> </p>
<p align="center"> <img src="assets/demo/noteweb3.png" alt="Note Taking" width="800" /> <br /> <em>📝 AI-readable notes with graph visualizations</em> </p>
1) What is Noteit MCP?
Noteit MCP is an HTTP MCP server (Next.js API route) that lets AI coding tools securely access two core systems:
- Agent Profiles: Composable configurations (personas, instructions, rules, documents) that shape AI behavior for specific tasks.
- Notes: Personal note-taking with structured records and graph visualizations.
Authentication uses OAuth 2.1 with device fingerprint for IDEs that support it, with an optional API Token flow for other MCP clients. The server endpoint is exposed at /api/mcp.
2) Why use Noteit MCP?
- Unified configuration: Reusable agent profiles that any AI client can adopt.
- Productive note-taking: AI-readable notes, tasks, and visual graphs.
- Secure by design: OAuth 2.1 + transparent token refresh; API token for non‑OAuth clients.
- Works across IDEs: Cursor, Claude Code, Gemini CLI, Claude Desktop (via proxy), and more.
<p align="center"> <img src="assets/prompt.png" alt="Noteit MCP UI" width="900" /> <br /> <em>60+ expert personas for different coding tasks and workflows</em> </p>
3) How to connect
The MCP server is at https://www.noteit-mcp.com/api/mcp.
Cursor (mcp.json)
Create or update ~/.cursor/mcp.json:
{
"mcpServers": {
"noteit-mcp": {
"url": "https://www.noteit-mcp.com/api/mcp"
}
}
}
Then restart Cursor. OAuth will be handled automatically.
Claude Code (built-in MCP)
Use the command-line helper (global scope):
claude mcp add --transport http noteit-mcp https://www.noteit-mcp.com/api/mcp
Or project scope:
claude mcp add -s project --transport http noteit-mcp https://www.noteit-mcp.com/api/mcp
Gemini CLI
Add the server and authenticate:
gemini mcp add --transport http noteit-mcp https://www.noteit-mcp.com/api/mcp
/mcp auth noteit-mcp
/mcp # verify tools are listed
Other IDEs (API Token)
Login at https://www.noteit-mcp.com to obtain an API token.
4) Available Tools
Through Noteit-MCP, agents can use the following tools:
- noteit_profiles_list: List user agent profiles - configuration sets containing personas, instructions, rules, and documents for specific roles or tasks
- noteit_profiles_getConfig: Retrieve a composable AI agent configuration profile containing personas, instructions, rules, and documents
- noteit_profiles_generate: Generate and save individual configuration components (persona, rule, document, instruction) that can be assembled into agent profiles
- noteit_notes_create: Create project notes with 4 specialized types: "note" for general records, "task" for development assignments, "why" for explanations, "issue" for problems and bugs
- noteit_notes_read: Retrieve complete content of a specific note by its unique ID
- noteit_notes_list: Browse and filter all user notes across projects with optional filtering by tags, record types, or project names
- noteit_web_create: Generate interactive HTML notes to help developers understand complex concepts, processes, or technical details
- noteit_flow_create: Create visual flow diagrams with nested data support for technical process visualization
⭐ Star this project
If Noteit MCP helps streamline your AI workflow, please give it a star! It helps others discover this tool and motivates continued development.
License
MIT
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.