Md-pdf

Markdown To PDF Conversion MCP
  • python

14

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "seanivore-convert-markdown-pdf-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/path/to/your/local/md-pdf-mcp",
        "run",
        "md-pdf-mcp"
      ]
    }
  }
}

md-pdf-mcp is a server that converts Markdown to PDF using VS Code-inspired styling and Python's ReportLab. It stores notes, supports summarization prompts, and exposes tooling to add notes and generate summaries, making it easy to produce styled PDFs from your Markdown notes and keep them organized.

How to use

You operate the server through an MCP client. Start the server using the provided runtime command, then connect your client to access resources, add new notes, and generate summaries. You can store notes with a name and text content, and you can create summaries of all stored notes with optional style preferences. Use the add-note tool to add new notes and the summarize-notes prompt to produce consolidated summaries. When you start the server via MCP, you will be able to access resources through the note:// URI scheme and interact with the tools and prompts exposed by the server.

Typical workflows you can perform:

  • Add a new note with a name and content
  • List and view existing notes via the note:// access path
  • Create a summary of all notes with an optional detail level (brief or detailed)
  • Generate a PDF from Markdown content using the styling rules provided by the server, then save or share the PDF as needed.

How to install

Prerequisites: you should have Python installed and access to an MCP runtime tool such as UV or UVX shown in the run commands below. You will also need a client capable of communicating with MCP servers.

Follow these steps to prepare and run the server locally:

# Step 1: Prepare your environment
# Create a project directory
mkdir -p ~/md-pdf-mcp && cd ~/md-pdf-mcp

# Step 2: Ensure you have the MCP runtime tooling installed (examples shown below depend on your setup)
# If you use the unpublished/dev path, you will run via UV with a local directory:
# uv --directory /Users/path/to/your/local/md-pdf-mcp run md-pdf-mcp

# If you use the published path, you can start via UVX with the package name:
# uvx md-pdf-mcp

# Step 3: Define the MCP server configuration in your client
# Use one of the following configurations in your MCP client settings (either unpublished or published setup):

# Unpublished server configuration (local development)
# This is a direct representation you can paste into your MCP client settings

{ "mcpServers": { "md-pdf-mcp": { "command": "uv", "args": [ "--directory", "/Users/path/to/your/local/md-pdf-mcp", "run", "md-pdf-mcp" ] } } }


# Step 4: Start the server locally using the configuration you chose
# If using the unpublished setup above, your client will initiate via the uv process as shown

# Step 5: Verify the server is running and ready to accept MCP connections
# Connect your MCP client and check for available resources (notes) and tools (add-note, summarize-notes)

Additional sections

Configuration details are contained in the MCP client setup sections above. The server exposes two main actions: add-note to store notes and summarize-notes to produce summaries of current content. Environment variables are not shown for running this server in the provided snippets. If you need to tailor runtime behavior, use the standard MCP client configuration flow with the provided command and arguments.

Available tools

add-note

Adds a new note to the server. Requires a name and content as input and updates the server state, notifying connected clients of the new resource.

summarize-notes

Summarizes all stored notes. Optional style parameter controls detail level (brief or detailed). Produces a combined prompt from all current notes and the chosen style.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational