MCP Servers 163

Document Parser

io.github.agenson-horrowitz/document-parser

B✓Verified

Parse and extract structured data from various document formats (PDF, Word, HTML).

Company Gi

io.github.Company-Gibraltar/company-gi

B✓Verified

Gibraltar company tools: corporate tax, compliance deadlines, and PDF form generation.

Read a URL as clean markdown, screenshot a website, url to PDF.

Screenshot API for AI agents: capture any public URL as JPEG, PNG, WebP, AVIF, or PDF.

Generate DOCX and PDF documents from your DocMake templates

vocce transcribe

io.github.cmoonagent/vocce-agent

B✓Verified

Agent media tools: transcribe, summarize, notes, flashcards, doc Q&A, PDF compress.

Deckprobe

io.github.deckflow/deckprobe

A✓Verified

Inspect PDF, Office, and iWork documents without rendering: counts, metadata, security signals

EN 16931: validate invoice data or a UBL/CII file, emit UBL or CII XML.

Invapi

io.github.invapi-org/invapi-mcp

D✓Verified

Extract, create, convert & validate invoices (UBL, CII, XRechnung, ZUGFeRD, PDF, Excel)

Convert PDF, Word, Excel, PowerPoint, EPUB, HEIC & images — 35+ tools from convertica.net

Keynote HarvestNew

io.github.hulin42/keynote-harvest-mcp

A✓Verified

Harvest Keynote and PDF slide decks into previews, text, image assets, and a manifest for agents.

Tailor resumes, generate cover letters, render CVs as PDF, and browse 22+ templates.

Convert PDF bank statements into transactions that arrive with a pass/fail reconciliation verdict.

MarkGrab

io.github.ArkNill/markgrab

B✓Verified

Universal web content extraction — any URL to LLM-ready markdown.

Scholar

io.github.mlintangmz2765/scholar

B✓Verified

Hardened Scholar MCP for deep academic research (Scopus, OpenAlex, Unpaywall) with PDF vision.

File operations for AI agents: HTML/Markdown to PDF, PDF tools, OCR, images.

Company Gibraltar

io.github.Company-Gibraltar/company-gibraltar

B✓Verified

Gibraltar company tools: corporate tax, compliance deadlines, and PDF form generation.

Generate PDF, DOCX, and XLSX documents from JSON data and create reusable templates via Docmill

Cyberwarex Web AccessNew

io.github.CyberPunk11147/cyberwarex-web-access

A✓Verified

Web access for agents: fetch, extract, screenshot, or PDF any public URL.