MCP servers · bytestay

Unfold MCP server: PDF, DOCX, PPTX and XLSX to Markdown

An MCP server that converts PDF, Word, PowerPoint and Excel documents to Markdown for AI agents, from a URL or a local file.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

The server gives an AI agent the content of PDF, DOCX, PPTX and XLSX documents as Markdown, taking either a public URL or a local file. It exposes one tool, convert_document, which accepts a url or path and an optional max_chars value (default 20000). The document format is detected from the content. Each call returns the Unfold API's JSON response, and when the marketplace reports it, a quota_remaining field showing the requests left on the plan that month. Errors are explained in plain words with a suggested next step.

An agent would reach for it when it needs the text of an office document or PDF in a form it can read. The server runs locally over stdio with uv and is released under the MIT licence. It calls the Unfold API, a paid service with a free plan, so the user supplies their own key from RapidAPI or api.market through an environment variable. Each tool call counts as one request on that plan. Without a key the server still starts, and the first tool call explains where to obtain one. Local files are read only when a tool call gives their path, and they are sent to the API for that single request. According to the publisher, the API processes inputs in memory and does not store them, and the key is sent only to the marketplace the user selected.

Limitations and requirements

Requires an API key from RapidAPI or api.market and a plan on the Unfold API; the free Basic plan allows 15 requests a month with a hard limit. Each tool call uses one request. Local files are limited to 10 MB and output Markdown to 500,000 characters. Requires Python 3.10 or later (uv installs it).

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    io.github.Bytestay/unfold-mcp

    PDF, DOCX, PPTX and XLSX documents to Markdown for AI agents, from a URL or a local file.

    v0.2.9
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
cloudflare

Cloudflare MCP servers

Cloudflare's hosted MCP servers for its products: documentation search, sandbox containers, browser rendering, Radar internet data, logs and analytics, Workers and more.

4.5K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 17 Nov 2026
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026