unfold-mcp
PDF, DOCX, PPTX and XLSX documents to Markdown for AI agents, from a URL or a local file.
What it does
unfold-mcp is an MCP server, a connector that lets an AI assistant use it as a tool. It is installed locally as a package and runs on your machine.
From the publisher's description, Electra Index matched it to 2 capabilities: document understanding and spreadsheet automation. That makes it a candidate for tasks such as answer questions from internal documents or analyze financial documents.
Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.
At a glance
How to connect
As declared in the Official MCP Registry · not tested by Electra IndexInstall package
- PYPI
bytestay-unfold-mcpv0.2.4 · runs locally (stdio)
MCP settings (Claude Desktop, Cursor and other MCP clients)
{
"mcpServers": {
"unfold-mcp-1": {
"command": "uvx",
"args": [
"bytestay-unfold-mcp"
]
}
}
}Tasks it helps with
Share of each task's required capabilities it covers| Answer questions from internal documents Document Understanding | 50% |
| Analyze financial documents Document Understanding | 50% |
| Extract data from PDFs Document Understanding | 50% |
| Fact-check a document Document Understanding | 50% |
| Prepare tax documents Document Understanding | 50% |
| Summarize long documents Document Understanding | 50% |
| Analyze patents Document Understanding | 50% |
| Review contracts Document Understanding | 50% |
Similar tools
Listed for the same task: answer questions from internal documents- LlmFilesREMOTELOCALConvert PDF, DOCX, XLSX and 25 other formats to clean Markdown for LLMs and RAG. No key or account
- PDF & Office to Markdown for RAGREMOTELOCALConverts PDF, scans, DOCX, XLSX and PPTX to Markdown with tables and page-aware RAG chunks
- PageIndex MCPREMOTELOCALReasoning-based RAG system for chatting with long PDFs. Supports local and online files
- PDF, Word, PowerPoint, Excel, HTML and EPUB to clean Markdown for RAG, with OCR. Pay per document
- doc.page PDF ExtractionREMOTELOCALExtract PDFs to Markdown, RAG chunks and cited tables; publish tracked Doc Links with read stats
- PDF Text Extractor (Apify Actor)REMOTELOCALExtract text, tables and RAG chunks from public PDF URLs; pay-per-event via your Apify account
Ready-made AI agents
- Free plan · Prices & score →
- Saner.AI48$8/mo · free plan · Prices & score →
- Flank32On quote · Prices & score →
- On quote · Prices & score →
Facts & evidence
Each fact shows where it was seen and when.| Fact | Value | Evidence | Source | Last confirmed |
|---|---|---|---|---|
| Install package | bytestay-unfold-mcp | DECLARED | SRC-001 Official MCP Registry | 5h ago |
| Package registries | pypi | DECLARED | SRC-001 Official MCP Registry | 5h ago |
| Local install (package) | yes | DECLARED | SRC-001 Official MCP Registry | 5h ago |
| Remote access (hosted) | no | DECLARED | SRC-001 Official MCP Registry | 5h ago |
| Website | https://unfold.bytestay.pt/integration.html#mcp-server | DECLARED | SRC-001 Official MCP Registry | 5h ago |
| Repository | https://github.com/bytestay/unfold-mcp | DECLARED | SRC-001 Official MCP Registry | 5h ago |
| Registry status | active | DECLARED | SRC-001 Official MCP Registry | 5h ago |
| Version | 0.2.4 | DECLARED | SRC-001 Official MCP Registry | 5h ago |
| MCP server | yes | DECLARED | SRC-001 Official MCP Registry | 5h ago |
Change history
- NEW06 Nov 2026first seen in the index
Is this page accurate?
Flag it and our robot re-checks the official source. Reports never change a score.Is unfold-mcp still online?
Free alerts · no account▲ 0Do you publish unfold-mcp? Get it seen by people choosing a tool
For publishers · optionalLaunch Spotlight: 60 days of clearly labelled Sponsored visibility on the use-case pages where unfold-mcp already appears, plus the weekly Pulse. No click in 60 days? The next 60 days are free.
Sponsored placements never change a score or a rank.
Are you the publisher of unfold-mcp?
Free · show your listingAn independent listing builds trust with your buyers. Announce it, and add the badge to your website or README.
<a href="https://electraindex.com/mcp/unfold-mcp-1?utm_source=badge&utm_medium=share&utm_campaign=listing"><img src="https://electraindex.com/api/badge/unfold-mcp-1" alt="Listed on Electra Index"></a>Questions about unfold-mcp
How do I connect unfold-mcp?
Install the PyPI package bytestay-unfold-mcp. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.
What can I use unfold-mcp for?
Based on its description, it is most relevant to: answer questions from internal documents, analyze financial documents, extract data from PDFs, fact-check a document.