Skip to main content
Glama
deenesjakoruzh
9Ninety

MCP Notes

by 9Ninety
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

📝 MCP Notes

MCP Notes Cover Image

✨ Overview

MCP Notes Server is a simple note-taking application built on top of the MCP protocol. Its purpose is to enable users to record and view complex notes and tasks while utilizing AI models, such as recording personal thoughts, notes, inspirations, and insights. It does not rely on creating project files, allowing users to record any content without making it public within the project.

This project includes two servers: a Node.js server using the Model Context Protocol (MCP) for AI-driven note management and a web server providing a user-friendly interface for manual interaction with your notes.

Note: This project requires DynamoDB for note storage. You'll need an AWS account to use it. AWS offers a generous free tier for DynamoDB, making it suitable for frequent personal use at no cost.

Related MCP server: Anki MCP Server

🎯 Core Features

  • 🖥️ Dual Server Architecture: MCP server for AI-driven note management and Web server for the user interface

  • 🤖 AI-Powered Note Taking: Record thoughts, insights, and tasks through AI interactions

  • 🗂️ Comprehensive Note Management: Create, list, retrieve, update, and delete notes via AI or web interface

  • 📋 Reliable Storage: Secure and efficient note storage with AWS DynamoDB

  • 🔐 Flexible Authentication: Support for AWS credentials via connection strings or environment variables

  • 📝 Project-Independent: Store personal notes without affecting project files or structure

🤖 Model Support

You can use any model that supports function calls as long as your client supports MCP. The following models have been tested and confirmed to work:

  • Claude 3.5 Series

  • Gemini 1.5 and 2.0 Series

  • GPT-4 Series

  • Mistral Large

  • Grok-2

  • DeepSeek Chat

🛠️ Installation

Recommended

Run directly with npx or bunx, see examples below.

Alternative

  1. Ensure Node.js is installed on your system.

  2. Clone this repository and install dependencies with: npm install

  3. Configure Claude Desktop or any other tools as shown below

⚙️ Credential Configuration

Connection String

dynamodb://<access_key>:<secret_key>@<region>/<table>

Example: dynamodb://AKIAXXXXXXXX:SKXXXXXXXX@us-east-1/mcp-notes

Environment Variables

  1. Export AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY.

  2. Supply connection information without credentials in the URI: dynamodb://us-east-1/mcp-notes

🤖 Integration with Tools

Claude Desktop

Add this snippet to claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-notes": {
      "command": "npx",
      "args": [
        "-y",
        "-p",
        "mcp-notes",
        "mcp-notes-server",
        "--dynamodb",
        "dynamodb://access_key:secret_key@region/table"
      ]
    }
  }
}

or file on local disks:

{
  "mcpServers": {
    "mcp-notes": {
      "command": "node",
      "args": [
        "file://path/to/notes-mcp-server.js",
        "--dynamodb",
        "dynamodb://access_key:secret_key@region/table"
      ]
    }
  }
}

Cody

Note: Currently, Cody has limited MCP server support.
It only allows one server connection and cannot make tool calls. You'll need to use the web interface to create and manage notes and then reference them in AI chat conversations.

Add this snippet to your VS Code settings:

{
  "openctx.providers": {
    "https://openctx.org/npm/@openctx/provider-modelcontextprotocol": {
      "nodeCommand": "node",
      "mcp.provider.uri": "file://path/to/notes-mcp-server.js",
      "mcp.provider.args": [
        "--dynamodb",
        "dynamodb://access_key:secret_key@region/table"
      ]
    }
  }
}

alternatively, use with npx (not guaranteed to work):

{
  "openctx.providers": {
    "https://openctx.org/npm/@openctx/provider-modelcontextprotocol": {
      "nodeCommand": "node",
      "mcp.provider.uri": "file:///usr/local/bin/npx",
      "mcp.provider.args": [
        "-y",
        "-p",
        "mcp-notes",
        "mcp-notes-server",
        "--dynamodb",
        "dynamodb://access_key:secret_key@region/table"
      ]
    }
  }
}

Cline

Add this snippet to cline_mcp_settings.json:

You will find a "MCP Server" icon next to the "New Task" button, and then there is an "Edit MCP Settings" button to open this file.

{
  "mcpServers": {
    "mcp-notes": {
      "command": "npx",
      "args": [
        "-y",
        "-p",
        "mcp-notes",
        "mcp-notes-server",
        "--dynamodb",
        "dynamodb://access_key:secret_key@region/table"
      ]
    }
  }
}

🚀 Running Web Servers

The web server provides a user-friendly interface for managing your notes. You can launch web interfaces to manage your notes, add new notes for AI, or modify parts of AI-generated notes.

npx -p mcp-notes mcp-notes-web-server --dynamodb "dynamodb://access_key:secret_key@region/table"
bun src/notes-web-server.ts --dynamodb "dynamodb://access_key:secret_key@region/table"

Alternatively, compile with npm run build and run node dist/notes-mcp-server.js or node dist/notes-web-server.js

Then navigate to http://localhost:3100 in your browser to view notes.

🔧 Available MCP Tools

listNotes

  • Input: { tags?: string[] }

  • Output: Array of all notes, optionally filtered by tags.

getNote

  • Input: { id: string }

  • Output: A single note object matching the given ID, or a "not found" message if no match exists.

writeNote

  • Input: { id: string, title: string, summary: string, tags: string[], content: string }

  • Output: A success confirmation message.

deleteNote

  • Input: { id: string }

  • Output: Deletion confirmation message 🚮.

📝 Data Structure

Notes are stored using the following structure:

  • id: A unique identifier for the note. It should be descriptive, with a random number suffix, like "meeting-notes-1362".

  • title: The title of the note.

  • summary: A short summary of the note's content.

  • tags: An array of tags associated with the note (e.g., ["meeting", "project-x"]).

  • content: The main content of the note.

📸 Screenshots

Claude Desktop

✅ Full functionality

Screenshot of MCP Notes Tool Call in Claude Desktop Screenshot of MCP Notes Resources in Claude Desktop

Cody

✅ Mention Notes via Resource

❎ Tool calls are not supported

Screenshot of MCP Notes in Cody

Cline

✅ Full functionality with Tool Calls

❓ Resources don't seem to work; help wanted.

Available Tools

4 tools
deleteNoteC

Deletes a specific note by its ID.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesID of the note to delete

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'Deletes' which implies a destructive mutation, but lacks details on permissions needed, whether deletion is permanent or reversible, error handling (e.g., invalid ID), or side effects. This leaves significant gaps for a destructive operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero wasted words. It is front-loaded with the core action ('Deletes'), making it easy to scan and understand quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive tool with no annotations and no output schema, the description is incomplete. It lacks critical information such as success/error responses, confirmation prompts, or behavioral nuances (e.g., cascading effects). The schema covers the parameter, but overall context for safe and effective use is insufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, with the parameter 'id' documented as 'ID of the note to delete'. The description adds minimal value beyond this, only reiterating 'by its ID' without providing additional context like ID format or examples. Baseline 3 is appropriate given the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Deletes') and resource ('a specific note'), making the purpose unambiguous. It specifies 'by its ID' which helps differentiate it from siblings like 'listNotes' or 'writeNote', though it doesn't explicitly contrast with them in the description text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'writeNote' for updates or 'getNote' for retrieval. It mentions the 'ID' parameter but doesn't explain prerequisites (e.g., note must exist) or exclusions (e.g., cannot delete non-existent notes).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

getNoteB

Retrieves a specific note by its ID.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesID of the note to retrieve

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves a note, implying a read-only operation, but doesn't cover aspects like error handling (e.g., what happens if the ID is invalid), authentication needs, rate limits, or return format. This leaves gaps in understanding how the tool behaves beyond the basic action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with zero waste—it directly states the tool's purpose without redundancy. It's appropriately sized for a simple retrieval tool and front-loaded with the essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (single parameter, no output schema, no annotations), the description is minimally adequate. It covers the basic action but lacks details on behavior, usage context, or output, which could be helpful for an agent. It meets the minimum viable standard but has clear gaps in completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, with the parameter 'id' fully documented in the schema as 'ID of the note to retrieve'. The description adds no additional meaning beyond this, such as format examples or constraints. Since the schema does the heavy lifting, the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Retrieves') and resource ('a specific note by its ID'), making the purpose immediately understandable. It doesn't explicitly distinguish from sibling tools like listNotes (which likely lists multiple notes) or deleteNote (which deletes), but the specificity of 'by its ID' implies it's for fetching a single, known note.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention siblings like listNotes for browsing notes or writeNote for creating/updating, nor does it specify prerequisites (e.g., needing a valid note ID). Usage is implied by the action but lacks explicit context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

listNotesB

Lists all notes, or search notes with tags you seen in previous list operation.

ParametersJSON Schema
NameRequiredDescriptionDefault
tagsNoOptional tags to filter notes. do not specify this if you didn't certainly sure what tags you want.

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool can list all notes or search with tags, but fails to describe critical behaviors: whether it's read-only (implied but not stated), how results are returned (e.g., pagination, format), error conditions, or any rate limits. This leaves significant gaps for an agent to understand operational traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two clear clauses, front-loading the main purpose ('Lists all notes') and adding a secondary function ('or search notes with tags'). There's no wasted text, though the phrasing 'tags you seen in previous list operation' is slightly awkward but still functional.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (list/search functionality), lack of annotations, and no output schema, the description is insufficiently complete. It doesn't explain return values, error handling, or behavioral constraints, leaving the agent with incomplete operational context. This is a significant gap for a tool without structured support.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, with the 'tags' parameter well-documented in the schema itself. The description adds minimal value beyond the schema by mentioning tags are for filtering and should be used only if certain, but doesn't provide additional context like tag format examples or interaction details. This meets the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Lists all notes, or search notes with tags'. It specifies the verb ('Lists'/'search') and resource ('notes'), making the function understandable. However, it doesn't explicitly differentiate from sibling tools like 'getNote' (which presumably retrieves a single note) or mention scope limitations, preventing a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides some implied guidance: it suggests using tags for filtering based on previous operations ('tags you seen in previous list operation'), which hints at a workflow. However, it lacks explicit instructions on when to use this tool versus alternatives like 'getNote' for single notes or 'writeNote' for creation, and doesn't specify prerequisites or exclusions, leaving usage context incomplete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

writeNoteC

Creates or updates a note with a unique ID suffixed by a random number.

ParametersJSON Schema
NameRequiredDescriptionDefault
contentYesContent of the note
idYesUnique identifier of the note, should be unique enough like "a-note-about-python-file-server-design-109".
summaryYesShort summary of the note
tagsYesTags of the note
titleYesTitle of the note, describe what was inside the content.

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden but provides minimal behavioral insight. It mentions the ID includes a random number suffix, hinting at uniqueness, but lacks details on permissions, error handling, or whether updates overwrite or merge. For a mutation tool, this is inadequate disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's function without redundancy. It's front-loaded and wastes no words, making it easy for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with 5 required parameters and no annotations or output schema, the description is insufficient. It doesn't explain return values, error conditions, or the implications of 'creates or updates' (e.g., idempotency), leaving significant gaps for agent usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameters are well-documented in the schema. The description adds no additional meaning beyond implying ID uniqueness with a random suffix, which is partially covered in the schema. Baseline 3 is appropriate as the schema handles most semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Creates or updates') and resource ('a note'), making the purpose evident. However, it doesn't explicitly differentiate from sibling tools like 'getNote' or 'listNotes', which would require mentioning that this is the primary write operation versus read-only siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an ID), compare to siblings like 'deleteNote', or specify scenarios for creation versus updates, leaving the agent without contextual usage cues.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 4 tool updatesv1.0.0
    • First observeddeleteNote
    • First observedgetNote
    • First observedlistNotes
    • First observedwriteNote
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.6/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: deleteNote removes notes, getNote retrieves single notes, listNotes lists or searches notes, and writeNote creates or updates notes. There is no overlap in functionality, making tool selection straightforward for an agent.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in camelCase (e.g., deleteNote, getNote, listNotes, writeNote). This uniformity enhances readability and predictability across the toolset.

Tool Count5/5

With 4 tools, this server is well-scoped for a notes management system. Each tool serves a distinct CRUD operation (create, read, update, delete), which is appropriate and efficient for the domain without being overly sparse or bloated.

Completeness5/5

The toolset provides complete CRUD coverage for notes: writeNote handles creation and updates, getNote and listNotes cover retrieval, and deleteNote handles deletion. There are no obvious gaps, enabling agents to perform full lifecycle operations on notes.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

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/9Ninety/MCPNotes'

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