Skip to main content
Glama

Flint Note

by disnet
MIT License
498
2

Flint Note

Flint note is a Model Context Protocol (MCP) server that provides an agent-first note-taking system designed from the ground up for AI collaboration. Instead of adding AI features to traditional notes, Flint treats AI agents as your primary interface for creating, organizing, and connecting your knowledge.

Key features

  • Agent-first design - AI agents understand your note types and guide you through creating structured content
  • Local markdown storage - Your notes are plain markdown files you own and control forever
  • MCP server architecture - Connects to any AI client that supports the Model Context Protocol
  • Intelligent note types - Each note type has its own agent instructions and metadata schema
  • Customizable AI behavior - Tell agents how to behave for each note type using natural language

Pre-requisites

How It Works

  1. flint-note server runs locally on your machine, managing your markdown files
  2. AI clients (like Claude Desktop) connect to the server via MCP
  3. AI agents can read your note types, understand their schemas, and help create content

Getting Started

Add flint-note to your client's MCP config:

{ "mcpServers": { "flint-note": { "command": "npx", "args": ["@flint-note/server@latest"] } } }
Adding Custom Prompts for Better AI Behavior

For the best experience, add a custom prompt that makes your AI assistant understand flint-note's agent-first design. The prompts/ directory contains optimized prompts for different AI models and platforms. If you want to get started quickly, just start your conversation by pasting in the following prompt:

You have access to flint-note, an intelligent note-taking system with multi-vault support designed for natural conversation-based knowledge management. ## COMMUNICATION STYLE: - **Be direct and substantive**: Focus on ideas and connections rather than praising user thinking - **Make genuine connections**: Link to related concepts without overstating their significance - **Avoid sycophantic language**: Replace "That's brilliant!" with "This connects to [concept]" - **Use connection-focused phrases**: "This relates to...", "Building on this idea...", "A related consideration is..." - **Acknowledge substance**: Focus on the intellectual merit of ideas rather than praising the person - **Maintain helpfulness**: Remain constructive and engaging without artificial enthusiasm ## CORE BEHAVIORS: - Be conversational: "I've added that to your work vault meeting notes" vs "Note created successfully" - Be proactive: extract action items, suggest connections, improve organization - Be vault-aware: understand current vault context and adapt behavior accordingly - Follow agent instructions: adapt behavior based on note type-specific agent instructions - Use metadata intelligently: validate and populate metadata schemas automatically - Use content hashes safely: always include content_hash when updating notes to prevent conflicts - Evolve continuously: suggest agent instruction improvements based on usage patterns ## ESSENTIAL WORKFLOW: 1. Check current vault context using get_current_vault when needed 2. Determine appropriate note type based on content and vault context 3. **ALWAYS use get_note_type_info to check agent instructions BEFORE creating notes** 4. Structure information meaningfully using note type guidelines and agent instructions 5. Extract actionable items: `- [ ] Task (Owner: Name, Due: Date)` 6. Follow agent_instructions returned from create_note for contextual follow-up 7. Use batch operations efficiently for creating or updating multiple related notes 8. **ALWAYS include content_hash when updating notes** - get current version first with get_note 9. Use search tools effectively for discovery and connections 10. Use update_note_type to refine agent instructions based on user feedback 11. Populate metadata schemas automatically when possible **CRITICAL**: NEVER create notes without first checking agent instructions with get_note_type_info ## VAULT MANAGEMENT: - Always understand which vault is currently active - Help users create and switch between vaults for different contexts (work, personal, research) - Provide vault-aware suggestions and organization - Use list_vaults, create_vault, switch_vault, get_current_vault as needed - Adapt behavior based on vault purpose and context ## AGENT INSTRUCTIONS SYSTEM: - **MANDATORY**: Check agent instructions with get_note_type_info before creating ANY note - Agent instructions define note type-specific behaviors - Follow them religiously for contextual assistance - Suggest improvements when you notice gaps or patterns - Use them to provide increasingly personalized experiences - Never create notes without understanding their behavioral requirements ## CONTENT HASH SAFETY: - **ALWAYS include content_hash when updating notes** - prevents conflicts and data loss - Get current note version with get_note before making updates - Handle CONTENT_HASH_MISMATCH errors by explaining conflicts and offering resolution - Include content_hash for each update in batch operations - Explain to users when conflicts occur: "The note was modified by another process" ## BATCH OPERATIONS: - Use batch create_note for 3+ related notes (project planning, imports, etc.) - Use batch update_note for bulk status changes or metadata updates - **Include content_hash for each update in batch operations** for safety - Handle partial failures gracefully - report success/failure counts with specific errors - Group related operations for efficiency - Provide clear feedback on batch results to users ## SEARCH SYSTEM: - **search_notes**: Fast full-text search with content ranking and type filtering - **search_notes_advanced**: Structured search with metadata filters, date ranges, and sorting - **search_notes_sql**: Direct SQL queries for complex analytical searches - Always use search to find related notes and suggest connections - Leverage metadata filters for precise discovery - Use FTS ranking to surface most relevant content ## RESPONSE PATTERNS: **Instead of excessive praise:** - "This connects to your existing work on [topic]..." - "This approach relates to [framework/concept]..." - "Building on this idea, you might consider..." - "This intersects with [related area]..." **Avoid phrases like:** - "That's such a powerful insight!" - "Brilliant observation!" - "You've identified something crucial!" - "What a thoughtful question!" **Focus on substance:** - Acknowledge the content of ideas without inflating their importance - Extend thoughts by connecting to relevant frameworks or examples - Suggest related areas worth exploring - Question constructively when appropriate - Clarify concepts that might deepen understanding Focus on making note-taking effortless while building a valuable, adaptive knowledge base across multiple organized vaults. Maintain genuine helpfulness while emphasizing the intellectual merit of ideas and their connections rather than praising the user's thinking.

Example Agent Conversations

Agent-Guided Note Creation

You: I just finished reading "The Psychology of Money"

Agent: I'll create a reading note for you. Based on your reading note schema, I need:

  • Your rating (1-5 stars)
  • Key insights that stuck with you
  • The author's name

What would you rate this book?

You: I'd give it a 4/5. Main insight was how behavior matters more than knowledge in investing.

Agent: Perfect! I'm creating your reading note with Morgan Housel as author, 4/5 rating, and that key insight. The note will be saved as reading/psychology-of-money.md

Intelligent Note Suggestions

You: Create a project note for our website redesign

Agent: I'll set up a project note. Based on your project schema, I should include:

  • Project goals and success criteria
  • Key milestones and deadlines
  • Team members and stakeholders
  • Risk assessment

What's the main goal for this redesign?

You: Improve user engagement and reduce support tickets by 30%

Agent: Excellent! I'll create projects/website-redesign.md with that goal and template sections for milestones, team, and risks. Should I link this to any existing notes?

Smart Metadata and Organization

You: Add a meeting note for today's standup

Agent: Creating your meeting note. I see you have a standup template that includes:

  • Attendees
  • What did we accomplish yesterday?
  • What are we working on today?
  • Any blockers?

Who attended today's standup?

You: The whole team - Sarah, Mike, Alex, and me

Agent: Got it! I'll create meetings/standup-2024-01-15.md with those attendees and the standup template. The metadata will automatically tag this as a "standup" meeting for easy filtering later. The note includes a content hash for safe future updates.

Safe Concurrent Updates

You: Update my project status to completed

Agent: I'll update your project note safely. Let me get the current version with its content hash first... Now updating with hash verification to prevent conflicts. ✅ Project status updated to completed with content hash protection.

You: What if someone else was editing it?

Agent: The content hash system would detect that conflict and alert me to get the latest version first. This prevents accidentally overwriting changes made by other agents or processes.

How Note Types Work

flint-note organizes your knowledge using note types - each with its own purpose, agent instructions, and metadata schema. Your workspace looks like this:

my-notes/ ├── .flint-note/ │ └── config.yml ├── reading/ │ ├── _description.md # Defines how agents help with reading notes │ ├── the-unaccountability-machine.md ├── projects/ │ ├── _description.md # Defines how agents help with projects │ ├── website-redesign.md │ └── mobile-app.md ├── meetings/ │ ├── _description.md # Defines how agents handle meeting notes │ └── team-standup-2024-01-15.md └── daily/ ├── _description.md # Defines daily note format and prompts └── 2024-01-15.md

Each _description.md file tells agents how to behave for that note type:

# Reading Notes ## Purpose Track books, articles, and papers with structured insights and ratings. ## Agent Instructions - Always ask for the author's background and credentials - Extract key insights and actionable takeaways - Request a personal rating (1-5 stars) and what made it memorable - Suggest connections to other readings in the vault - Encourage specific quotes with page references ## Metadata Schema - title: Book/article title (required, string) - author: Author name (required, string) - rating: Personal rating (required, number, min: 1, max: 5) - status: Reading progress (required, select: to_read|reading|completed) - tags: Topic categories (optional, array) - isbn: ISBN for books (optional, string)

Customizing Agent Behavior

You can modify how agents work with any note type just by talking to them:

You: Update my reading notes so agents always ask about the book's publication year

Agent: I'll update your reading note instructions to include asking about publication year.

[Updates reading/_description.md with the new instruction]

You: Make project notes more focused on deadlines and blockers

Agent: I'll modify your project note instructions to emphasize deadline tracking and proactive blocker identification.

[Updates projects/_description.md accordingly]

Configuration

Flint Note automatically manages its configuration and will upgrade older vaults seamlessly. The configuration is stored in .flint-note/config.yml in each vault.

Configuration Settings

Key configuration sections include:

  • deletion: Controls note and note type deletion behavior
    • require_confirmation: Requires explicit confirmation for deletions (default: true)
    • create_backups: Creates backups before deletion (default: true)
    • backup_path: Where to store backups (default: .flint-note/backups)
    • allow_note_type_deletion: Allows deletion of entire note types (default: true)
    • max_bulk_delete: Maximum notes that can be deleted in one operation (default: 10)

Tutorial

Check out our tutorial for a more detailed guide on how to use Flint Note.

Design

See design.md for design and architecture of the system.

-
security - not tested
A
license - permissive license
-
quality - not tested

Provides an agent-first note-taking system designed from the ground up for AI collaboration. Organizes your notes as a local vault of ordinary markdown files with semantic note types.

  1. Key features
    1. Pre-requisites
      1. How It Works
      2. Getting Started
    2. Example Agent Conversations
      1. Agent-Guided Note Creation
      2. Intelligent Note Suggestions
      3. Smart Metadata and Organization
      4. Safe Concurrent Updates
    3. How Note Types Work
      1. Customizing Agent Behavior
    4. Configuration
      1. Configuration Settings
    5. Tutorial
      1. Design

        Related MCP Servers

        • A
          security
          A
          license
          A
          quality
          A simple note-taking MCP server for recording and managing notes with AI models.
          Last updated -
          4
          66
          21
          TypeScript
          GPL 2.0
        • -
          security
          F
          license
          -
          quality
          Enables AI language models to interact with Microsoft OneNote via a standardized interface, supporting notebook and page management through natural language.
          Last updated -
          107
          6
          TypeScript
        • -
          security
          F
          license
          -
          quality
          Facilitates note storage and summarization through custom URIs, allowing users to manage, summarize, and update notes with varying detail levels in a collaborative environment.
          Last updated -
          Python
          • Apple
        • A
          security
          F
          license
          A
          quality
          This server provides a note storage system with a custom URI scheme, allowing users to add and summarize notes, with adjustable summary detail levels.
          Last updated -
          1
          Python
          • Apple

        View all related MCP servers

        MCP directory API

        We provide all the information about MCP servers via our MCP API.

        curl -X GET 'https://glama.ai/api/mcp/v1/servers/disnet/flint-note'

        If you have feedback or need assistance with the MCP directory API, please join our Discord server