MCP Pandoc

🚀 MCP-Pandoc Usage Instructions

📦 Installation

Method 1: Manual Installation via the claude_desktop_config.json Configuration File

• On a MacOS system, open the path: ~/Library/Application\ Support/Claude/claude_desktop_config.json
• On a Windows system, open the path: %APPDATA%/Claude/claude_desktop_config.json

"mcpServers": {
  "mcp-pandoc": {
    "command": "uv",
    "args": [
      "--directory",
      "<DIRECTORY>/mcp-pandoc",
      "run",
      "mcp-pandoc"
    ]
  }
}

"mcpServers": {
  "mcp-pandoc": {
    "command": "uvx",
    "args": [
      "mcp-pandoc"
    ]
  }
}

Method 2: Automatic Installation of the Released Server Configuration via Smithery

Run the following bash command to automatically install the released mcp-pandoc pypi for Claude Desktop via Smithery:

npx -y @smithery/cli install mcp-pandoc --client claude

Note: If you need to use the locally configured mcp-pandoc, follow the steps in the "Development/Unreleased Server Configuration" section above.

💻 Development Guide

Build and Release

To prepare the package for release:

1. Synchronize dependencies and update the lock file:

uv sync

2. Build the release distribution:

uv build

This command will create source code and wheel files in the dist/ directory.

3. Publish to PyPI:

uv publish

Note: You need to set your PyPI credentials via environment variables or command-line arguments:

• Token: --token or UV_PUBLISH_TOKEN
• Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since the MCP server runs via standard input and output, debugging can be challenging. For the best debugging experience, we highly recommend using MCP Inspector.

You can start the MCP Inspector with the following command:

npx @modelcontextprotocol/inspector uv --directory /Users/vivekvells/Desktop/code/ai/mcp-pandoc run mcp-pandoc

After starting, the Inspector will display a URL that you can access in your browser to begin debugging.

🤝 Contribution Guide

We welcome contributions to mcp-pandoc! Here are some guidelines on how to get involved in the project:

Submitting Issues

If you encounter any issues, please submit them via GitHub Issues. Before submitting, search for existing issues to ensure yours hasn't been reported.

Submitting Features or Fixes

1. Fork the repository: First, fork this project to your own account.
2. Create a branch: Create a separate branch for your new feature or fix. It's recommended to use a meaningful branch name, such as feature/new-feature or bugfix/issue-123.
3. Commit your code: Before committing, ensure your code adheres to the project's coding standards and add detailed commit messages.
4. Create a Pull Request: After pushing your branch to your forked repository, create a Pull Request to the main branch of the original project.

Contribution Guidelines

• Issue Reporting: Provide clear steps to reproduce the issue and relevant logs to help developers quickly identify the problem.
• Code Contribution: Follow the project's coding conventions, ensure consistent code style, and add appropriate documentation comments.
• Documentation Updates: If you have suggestions for improving the documentation, submit a Pull Request to update the relevant documentation.

Thank you for your interest and support! We hope mcp-pandoc meets your needs, and we welcome any feedback and collaboration.