Claude MarketplacesSubmit
shan-zhu avatar

shuck-file

shan-zhu/shuck-file

Converts Word, PDF, Excel, PowerPoint, and CSV files into clean Markdown, with smart routing that depends on file size. Small documents get converted directly. Large ones return a document map showing sections, token counts, and density metrics, so your agent can pull only what it needs with targeted section extraction or keyword search. The MCP server exposes two tools: shuck for conversion with options like sections filtering, grep search, and token budgets, and list_formats for checking supported file types. Useful when you need an agent to work with office documents without dumping entire 50 page reports into context, or when you want structured extraction from spreadsheets and presentations.

GitHub stars
6
tools
2
transport
STDIO
last updated
Mar 20, 2026
View on GitHub

Tools

2 tools

Public tool metadata for what this MCP can expose to an agent.

shuckConvert a document to Markdown with all options (mode, sections, grep, budget, etc.)

Convert a document to Markdown with all options (mode, sections, grep, budget, etc.)

No parameter schema in public metadata yet.

list_formatsList supported document formats

List supported document formats

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

πŸ‡¨πŸ‡³ δΈ­ζ–‡

shuck-file

PyPI MCP Registry License: MIT

Any file in, Markdown out β€” read only what matters.

shuck-file converts documents to clean Markdown for AI agents and LLMs. Small files output directly; large files return a document map with section summaries, token counts, and actionable next steps β€” so agents only pull what they need.

Why shuck-file?

AI agents need a bridge that's context-aware:

  • Small file β†’ shuck report.docx β†’ full Markdown on stdout
  • Large file β†’ shuck report.docx β†’ document map with sections and extraction options
  • Targeted extraction β†’ shuck report.docx --sections s1,s3 β†’ only what you need
  • Search β†’ shuck report.docx --grep "revenue" β†’ find without reading everything

Supported Formats

View the full README on GitHub

Details

Repository
github.com/shan-zhu/shuck-file
Category
Documents & Knowledge
Package
shuck-file
Transport
STDIO
Registry
MCP registry, active

More from shan-zhu

Related Documents & Knowledge MCP servers

View all
1mlorentedev avatarHive Vaultmlorentedev/hiveOn-demand Obsidian vault access for AI coding assistants β€” 17 tools, 5 resources, 4 prompts.5stars
2psychquant avatarChe Word Mcppsychquant/che-word-mcpSwift-native MCP server for Word (.docx) manipulation with 148 tools5stars
3adelelo13 avatarNeuromcpadelelo13/neuromcpSemantic memory for AI agents with hybrid search, knowledge graph, and consolidation4stars
4getalai avatarPresentationsgetalai/alai-mcp-serverGenerate, edit, and export AI presentations to PDF, PPTX, or a shareable link.4stars
5indhar01 avatarMemographindhar01/memographGraph-based memory system for LLMs with knowledge graphs and semantic search.4stars
6entire-vc avatarEvc Team Relay Mcpentire-vc/evc-team-relay-mcpMCP server for AI agent read/write access to Obsidian vaults via EVC Team Relay.3stars