Sticky Notes
AI Sticky Notes MCP Server
An MCP server that lets an AI assistant save, read, and summarize personal notes. Notes are stored in a local notes.txt file next to the server.
Features
add_notetool: Append a new note.read_notestool: Read all saved notes.notes://latestresource: Retrieve the most recently added note.note_summary_promptprompt: Create a prompt containing the current notes for summarization.
Related MCP server: Sticky Notes MCP Server
Requirements
Python 3.12 or newer
pipor uv
Run Locally
Using uv
uv sync
uv run python main.pyUsing pip
Create and activate a virtual environment, then install the dependency:
python -m venv .venv
.venv\Scripts\Activate.ps1
pip install -r requirements.txt
python main.pyThe server communicates over MCP stdio, so it is normally launched by an MCP-compatible client rather than opened directly in a browser.
Test the Server
With the MCP CLI installed, start the MCP Inspector with:
mcp dev main.pyUse the Inspector to call add_note, read_notes, open the notes://latest resource, and run note_summary_prompt.
You can also verify the Python module and syntax directly:
uv run python -c "import main; print('MCP server import ok')"
uv run python -m py_compile main.pyDeploy with Smithery
The repository includes smithery.yaml, which configures Smithery to start the server with:
startCommand:
type: stdio
command: python
args: ["main.py"]Push the deployment files to a GitHub repository and deploy that repository through Smithery. The important files are:
main.pyrequirements.txtsmithery.yaml
notes.txt is optional because the server creates it automatically when needed. Include it only if you want to ship the sample notes.
Run with Docker
Build and start the included image:
docker build -t ai-sticky-notes .
docker run --rm -i ai-sticky-notesProject Structure
main.py MCP server implementation
requirements.txt Python dependencies
smithery.yaml Smithery stdio startup configuration
Dockerfile Container build configuration
notes.txt Local note storage, created automatically if absentStorage Note
Notes are stored in a plain text file. This is suitable for local use and demonstrations, but hosted containers may not preserve the file across restarts or redeployments. Durable production storage should use an external database or persistent volume.
This server cannot be installed
Maintenance
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to create, read, and summarize sticky notes stored in a local text file through MCP tools, resources, and prompts.
- AlicenseAqualityDmaintenanceEnables creating, reading, updating, and deleting sticky notes with persistent text file storage through the MCP protocol.4MIT
- AlicenseAqualityBmaintenancePersistent sticky notes for Claude Code. You pin a note — a decision, a blocker, a todo — and it survives session resets, /clear, and closing the terminal. Next time you open Claude in that project, the notes that still matter are handed back to it automatically.33021MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to save and retrieve persistent sticky notes across conversations, with tools, a resource, and a prompt for note management and summarization.
Related MCP Connectors
Cross-session, cross-device memory for your agent: remember and recall notes. No key to start.
Feedback layer for video. Reviewers talk through feedback; agents read it as structured comments.
Search, save, and set reminders in your personal MarkIt library of links, posts, and notes.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/Sheheryar-Ahmad/Sticky-Notes-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server