md-pdf-mcp
Converts Markdown to styled PDFs using VS Code's markdown styling and Python's ReportLab.
md-pdf-mcp (Markdown to PDF MCP Server)
Convert Markdown to gorgeously styled PDFs using VS Code's markdown styling and Python's ReportLab.
Components
Resources
The server implements a simple note storage system with:
- Custom note:// URI scheme for accessing individual notes
- Each note resource has a name, description and text/plain mimetype
Prompts
The server provides a single prompt:
- summarize-notes: Creates summaries of all stored notes
- Optional "style" argument to control detail level (brief/detailed)
- Generates prompt combining all current notes with style preference
Tools
The server implements one tool:
- add-note: Adds a new note to the server
- Takes "name" and "content" as required string arguments
- Updates server state and notifies clients of resource changes
Configuration
[TODO: Add configuration details specific to your implementation]
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.jsonOn Windows: %APPDATA%/Claude/claude_desktop_config.json
Development/Unpublished Servers Configuration ``` "mcpServers": { "md-pdf-mcp": { "command": "uv", "args": [ "--directory", "/Users/path/to/your/local/md-pdf-mcp", "run", "md-pdf-mcp" ] } } ``` Published Servers Configuration ``` "mcpServers": { "md-pdf-mcp": { "command": "uvx", "args": [ "md-pdf-mcp" ] } } ```
Development
Building and Publishing
To prepare the package for distribution:
- Sync dependencies and update lockfile:
uv sync
- Build package distributions:
uv build
This will create source and wheel distributions in the dist/ directory.
- Publish to PyPI:
uv publish
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token:
--tokenorUV_PUBLISH_TOKEN - Or username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory /Users/seanivore/Development/md-pdf-mcp run md-pdf-mcp
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
相关服务器
Notion
Connects AI assistants to your Notion workspace to search and manage pages, databases, and content.
Notion
Integrate with Notion workspaces to manage databases, pages, and content.
Squad AI
Your AI Product Manager. Surface insights, build roadmaps, and plan strategy with 30+ tools.
Decent Sampler Drums
Generates Decent Sampler drum kit configurations.
prototype assistant
The MCP tool that allows AI to directly create prototypes based on HTML enables rapid construction of software prototypes even without Figma or Axure.
Microsoft Planner by CData
A read-only MCP server enabling LLMs to query live Microsoft Planner data using the CData JDBC Driver.
harvest-mcp-server
Harvest time tracking integration with 40+ tools for managing time entries, projects, clients, tasks, and generating time reports via the Harvest API v2
Freshdesk
Integrates with Freshdesk to manage support tickets, contacts, and other customer service operations.
Roam Research
Connects AI assistants to your Roam Research graph for data access and interaction.
Google Calendar
An MCP server for creating and managing Google Calendar events.