Markdown Notes MCP Server
Enables reading and managing markdown note files from a specified directory through natural language interactions.
README
Markdown Notes MCP Server
This project provides a simple MCP (Model Context Protocol) server for managing markdown notes. It's built using the fastmcp library.
Prerequisites
- Python 3.10 or newer
uvpackage manager
Installation
-
Install
fastmcpand project dependencies:This project uses
uvfor dependency management. Running the command below will installfastmcpand any other dependencies listed inpyproject.toml.uv pip install fastmcp
Configuration
The server's behavior can be customized via the following environment variable:
MD_NOTES_PATH: Specifies the root directory for all note-related operations. If this variable is not set, the server will default to using the current working directory. Both thelist_notesandread_notetools will resolve file and directory paths relative to this base path.
Running the Server
You can run the server in two modes: run for production/consumption and dev for development and testing.
Run Mode
This mode is for running the server to be used by the Gemini CLI. The main.py script can now be run directly as it contains the server startup logic.
python main.py
You should see output similar to this:
[12/13/25 17:52:18] INFO Starting MCP server 'MarkdownNotes' with transport 'http' server.py:2582
on http://127.0.0.1:8080/mcp
INFO: Started server process [24263]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8080 (Press CTRL+C to quit)
Dev Mode
This mode starts the MCP Inspector, a web application that allows interactive testing of the tools provided by the MCP server.
fastmcp dev main.py --ui-port="9080" --server-port="5080"
You will see output like this, including a URL to access the MCP Inspector:
Starting MCP inspector...
ā Proxy server listening on localhost:5080
š Session token: <your_session_token>
Use this token to authenticate requests or set DANGEROUSLY_OMIT_AUTH=true to disable auth
š MCP Inspector is up and running at:
http://localhost:9080/?MCP_PROXY_PORT=5080&MCP_PROXY_AUTH_TOKEN=<your_session_token>
š Opening browser...
Connecting to Gemini CLI
To use this MCP server with the Gemini CLI, you need to add it as a source.
gemini mcp add --transport http mdnotes http://127.0.0.1:8080/mcp
After adding the server, you can use the /mcp command in the Gemini CLI to see the available tools.
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.
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.
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.
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.