mcp -to-markdown

MCP server from FradSer/mcp-server-to-markdown

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio fradser-mcp-server-to-markdown mcp-server-to-markdown \
  --env CLOUDFLARE_API_TOKEN="your_api_token" \
  --env CLOUDFLARE_ACCOUNT_ID="your_account_id"

How to use

This MCP server, mcp-server-to-markdown, provides a standardized interface to convert a variety of file formats into Markdown descriptions by leveraging Cloudflare AI services. It exposes a tool named to-markdown that takes file paths as input and returns a JSON array with each item containing the original filename, its mime type, a generated Markdown description, and a token count. You can integrate this server into your MCP client setup to streamline document and content conversion tasks across your workflows. The server is designed to work with common document, image, web content, data, and spreadsheet formats, translating them into human-readable Markdown descriptions suitable for documentation, summaries, or cataloging.

Usage is typically done by configuring the MCP client (Cursor, Claude Desktop, or ChatWise) to point to the to-markdown MCP server. The key configuration is to set the command to mcp-server-to-markdown and provide the required environment variables for Cloudflare access: CLOUDFLARE_API_TOKEN and CLOUDFLARE_ACCOUNT_ID. Once configured, you can send filePaths arrays to the tool and receive structured Markdown descriptions in response.

How to install

Prerequisites:

Node.js 18 or later
npm (comes with Node.js)
A Cloudflare API token with appropriate permissions and your Cloudflare Account ID

Installation steps:

Install the MCP server globally (Node.js):

npm install -g mcp-server-to-markdown

Start the MCP server (example):

mcp-server-to-markdown

Alternatively, install via Smithery for CLI integration (metadata from README):

npx -y @smithery/cli install @FradSer/mcp-server-to-markdown --client claude

Create or update your MCP client configuration to route to the to-markdown server (see mcp_config in this document). Ensure CLOUDFLARE_API_TOKEN and CLOUDFLARE_ACCOUNT_ID are set in the environment where the server runs.
Verify installation by invoking the tool with a test set of file paths to ensure Markdown outputs are generated as expected.

Additional notes

Tips and common considerations:

Ensure your Cloudflare API token has access to the required Cloudflare AI services and that your account ID is correct.
The server supports a range of file formats including PDFs, JPEG/PNG/WebP/SVG images, HTML, XML/CSV data, and multiple spreadsheet formats. If a file type isn’t processed as expected, verify the file contents and mime type recognition.
When deploying in production, consider securing the environment variables and restricting MCP client access to trusted clients.
If you encounter mismatches in input file paths, validate that the MCP client is passing absolute paths or correctly resolved paths in the host environment.
The API returns an array of results; each entry includes filename, mimeType, description, and tokens for budgeting or auditing purposes.

Related MCP Servers

zen

1.1k

Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage

MCP -Deepseek_R1

A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)

mcp-fhir

A Model Context Protocol implementation for FHIR

mcp

Inkdrop Model Context Protocol Server

mcp-appium-gestures

This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..

dubco -npm

The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.