About unfold-mcp
unfold-mcp converts PDF, DOCX, PPTX and XLSX files from URLs or local paths into Markdown for AI agents. It runs locally over stdio and uses the Unfold API with a marketplace key.
Key features
- 01Convert PDF, DOCX, PPTX and XLSX
- 02Accept URLs and local files
- 03Detect document format automatically
- 04Return Markdown with configurable character limit
Use cases
- 01Extract text from a report for an AI agent
- 02Turn a spreadsheet or presentation into Markdown
- 03Process a document from a public URL
MCP support
This MCP server exposes a document-conversion tool to MCP clients. It runs locally over stdio and calls the Unfold API.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx bytestay-unfold-mcpRAPIDAPI_KEYSecretYour RapidAPI keyAPI_MARKET_KEYSecretYour api.market key, used when RAPIDAPI_KEY is not setBYTESTAY_MARKETPLACErapidapi or apimarket, when both keys are set (the old name HFL_MARKETPLACE still works)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEUnfold MCP server
Give your AI agent the content of PDF, Word (DOCX), PowerPoint (PPTX) and Excel (XLSX) documents as Markdown, from a URL or a local file.
The server is open source (MIT). It calls the Unfold API, which is paid, with a free plan.
- You use your own key, from RapidAPI or api.market.
- Every tool call is one request on your plan.
- The free Basic plan has 15 requests a month, with a hard limit, so it never runs up a bill.
1. Get a key
| marketplace | |
|---|---|
| RapidAPI | plans |
| api.market | store |
2. Add the server to your MCP client
The server runs locally over stdio with uv. Put your key in its environment.
JSON configuration (Claude Desktop, Cursor, VS Code and most clients):
{
"mcpServers": {
"unfold": {
"command": "uvx",
"args": ["--from", "bytestay-unfold-mcp", "unfold-mcp"],
"env": { "RAPIDAPI_KEY": "your-rapidapi-key" }
}
}
}
Claude Code:
claude mcp add unfold --env RAPIDAPI_KEY=your-rapidapi-key -- uvx --from bytestay-unfold-mcp unfold-mcp
Environment
| variable | meaning |
|---|---|
RAPIDAPI_KEY | your RapidAPI key |
API_MARKET_KEY | your api.market key, used when RAPIDAPI_KEY is not set |
HFL_MARKETPLACE | rapidapi or apimarket, when both keys are set |
Without a key the server still starts. The first tool call then explains where to get one.
Also listed on Glama:
3. Tools
| tool | what it does |
|---|---|
convert_document(url=… | path=…, max_chars=20000) | converts one document to Markdown; give a public URL, or a local file to upload |
The format is detected from the content.
Every tool returns the API's JSON response.
- When the marketplace reports it,
quota_remainingis added: the requests left on your plan this month. - Errors are explained in plain words, with what to do next:
- key refused, with the link to subscribe;
- quota reached, with the plans;
- input the API couldn't process, with the API's reason.
Privacy
- Local files are read only when a tool is given their path. They are sent to the API for that one request.
- The API processes inputs in memory and doesn't store them. See the privacy policy.
- Your key is only sent to the marketplace you chose.
Limits
- Local files up to 10 MB.
- Markdown up to 500,000 characters.
- The server needs Python 3.10+ (uv installs it for you).
Development
uv venv && uv pip install -e ".[dev]"
.venv/bin/pytest # unit tests, no network; 100% coverage required
.venv/bin/ruff check src tests scripts
scripts/e2e_stdio.py unfold runs the server over stdio, as a client would, and calls its tools against the real API. It needs RAPIDAPI_KEY or API_MARKET_KEY.
Licence
MIT. Unfold itself is a paid API with a free plan, run by ByteStay.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.