Pandoc MCP Server

What does “pandoc” MCP Server do?

The “pandoc” MCP Server is a Model Context Protocol server designed for seamless document format conversion using the powerful pandoc tool. It acts as an intermediary, allowing AI assistants and clients to transform content between various document formats (such as Markdown, DOCX, HTML, etc.) while preserving the formatting and structure of the original documents. This significantly enhances development workflows by enabling automated document conversions as part of larger AI-powered flows, making it easier to integrate with APIs, file systems, and other external data sources. The server is particularly useful for tasks where maintaining document fidelity across formats is critical and supports extensibility for future additions like PDF support.

List of Prompts

No specific prompt templates are mentioned in the available documentation.

List of Resources

No explicit resources are documented in the available repository files.

List of Tools

• Document Format Conversion
  Provides an interface for converting documents between various formats using pandoc. Allows clients to specify input and output formats, and handles the transformation while retaining formatting and structure.

Use Cases of this MCP Server

• Automated Document Conversion:
  Integrate with AI assistants to automatically convert documents between formats (e.g., Markdown to DOCX or HTML), streamlining workflows for technical writers and developers.
• Content Publishing Pipelines:
  Transform source files into multiple formats for publishing (e.g., converting academic papers into HTML, PDF, or LaTeX for different platforms).
• Collaboration Across Tools:
  Enable teams using different document editors and systems to collaborate seamlessly by converting files to their preferred formats.
• Data Migration and Archiving:
  Migrate legacy documents to modern formats or archive content in standardized, widely supported formats.
• Developer Workflow Integration:
  Use as part of continuous integration/continuous deployment (CI/CD) pipelines to ensure documentation is always up to date in multiple formats.

How to set it up

Windsurf

1. Install prerequisites: Ensure Node.js and pandoc are installed.
2. Locate configuration: Open your Windsurf configuration file.
3. Add the pandoc MCP server: Insert the following JSON in the mcpServers section:

   {
     "pandoc": {
       "command": "npx",
       "args": ["@pandoc/mcp-server@latest"]
     }
   }
   

4. Save and restart Windsurf: Apply the configuration changes.
5. Verify setup: Check in the Windsurf UI that the server appears and is running.

Securing API Keys (if required):

{
  "pandoc": {
    "command": "npx",
    "args": ["@pandoc/mcp-server@latest"],
    "env": {
      "API_KEY": "${PANDOC_API_KEY}"
    },
    "inputs": {
      "api_key": "${PANDOC_API_KEY}"
    }
  }
}

Claude

1. Install prerequisites: Ensure Node.js and pandoc are installed.
2. Edit configuration: Open your Claude settings or config file.
3. Add server configuration:

   {
     "pandoc": {
       "command": "npx",
       "args": ["@pandoc/mcp-server@latest"]
     }
   }
   

4. Save changes and restart Claude.
5. Verify setup: Confirm the pandoc MCP server is listed and active.

Cursor

1. Ensure Node.js and pandoc are installed.
2. Open Cursor’s configuration file.
3. Insert MCP server JSON:

   {
     "pandoc": {
       "command": "npx",
       "args": ["@pandoc/mcp-server@latest"]
     }
   }
   

4. Restart Cursor to apply changes.
5. Check MCP server availability in the Cursor interface.

Cline

1. Install Node.js and pandoc.
2. Access Cline’s configuration file.
3. Add the following under mcpServers:

   {
     "pandoc": {
       "command": "npx",
       "args": ["@pandoc/mcp-server@latest"]
     }
   }
   

4. Save and restart Cline.
5. Ensure proper operation by checking the Cline dashboard.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "pandoc": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “pandoc” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Between these two tables, I’d rate the mcp-pandoc MCP server as a solid 6/10 for documentation and developer readiness. While it provides a clear overview and usage instructions, it lacks details on prompt templates, resources, and advanced MCP features such as roots or sampling.

MCP Score