Documents and PDF MCP Servers
Parsing, extraction and OCR for documents an assistant cannot read on its own. 800 servers in the registry match this topic; 13 of the top ones are answering right now, exposing 209 tools between them. Checked every 15 minutes.
800 in this topic 13 of the top answering checked every 15 min
Ranked by uptime and installs
how the ranking worksAPICK Korean data, OCR, search, conversion, image and video generation, and asynchronous TTS
Deterministic DOCX/PPTX/XLSX/PDF parser: track changes, comments, headers, footers, merged cells.
Process video, audio, images, and documents with 86+ cloud media processing robots.
EN 16931: validate invoice data or a UBL/CII file, emit UBL or CII XML. XRechnung, Peppol. Not PDF.
Photo management for self-hosted Immich: search, albums, duplicates, faces, PDF reports. 94 tools.
Convert PDFs and other documents to structured formats via Docling, for AI applications.
Search hpt.su — Russian/EAEU vehicle compliance documents: type approvals, certificates, VIN lookup.
Section-level doc search for .md, .rst, .adoc, .ipynb, .html, .yaml, .json, and OpenAPI specs.
Convert files, run PDF/image tools, create billing links, and report feedback.
Local-first document MCP for AI agents: create, read, secure and sign PDF/Word/Excel/PPTX.
Query a verified document collection: passages that answer a question, with their source.
Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
Generate PDF/DOCX/XLSX/PPTX from templates+JSON. Convert Office/HTML/MD to PDF. Universal templating
Zotero MCP server for Claude and ChatGPT: search, citations, safe writes, PDF passages and pages.
Deterministic doc-drift detection: guard, score, explain, verify-claims and diagnose MCP tools.
MCP server for PDF generation, parsing, splitting, merging, and manipulation via oxidize-pdf
Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.
Resolve documentation ownership, edit roots, checks, and human handoffs before an agent edits code.
Word (.docx) MCP server: 221 operations, live editing, tracked changes, citations, mail merge.
Schema, database, document, user and dev-server tools for a Rebase backend project.
Local MCP server: recordings or public video URLs into transcript, frames, OCR, wall-clock evidence.
Letterhead PDF as digital stationery: prints Markdown without overprinting header, footer, or logo.
Evidence-first PDF MCP. Agent Document Twin with citeable page+bbox evidence.
Publish pages, documents, or folders to a link; documents render as pages; updates keep the URL.
Convert PDF bank statements to checked Excel, CSV or JSON with balance validation.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Academic paper knowledge-base MCP server: PDF ingest, vector search with reranking, KB management.
Provider-fixed web search plus transparent URL, DOI, and document fetching
Federated academic search, citation traversal, persistent PDF download, and temporary reading.
Use your own Word templates to convert Markdown → DOCX/PDF/HTML from any MCP-compatible AI.
Render HTML, Markdown, or URLs to images, PDF, or branded artifacts; extract and watch pages.
Turn URLs, files and text into media, transcripts, summaries, translations and PDF.
Local file tools for agents: documents, PDFs, images, QR codes. Nothing is uploaded.
Convert PDF/CSV to Markdown with AI-powered OCR via the PromptReady cloud API.
50 spreadsheet tools for .xlsx: recalc formulas, repair broken refs, read/write, diff, audit.
Classify documents, extract structured fields, mask PII, export JSONL/RAG datasets for AI agents.
MCP server for Siglio. Lets an AI assistant send documents for e-signature by email or text.
Answer questions from documents too large to fit in context, reading only the sections you need.
Edit Office documents and prove no edit went unrecorded
Automated DOCX Redlining Engine
MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input
Local-first documentation for AI agents. Offline, instant, private doc retrieval.
One section in, one section out — on Markdown/GEML files, bad writes refused.
MinerU document parsing API — PDFs, images, DOCX, PPTX with OCR and batch processing.
PDF-to-Markdown extraction that audits its own output and flags any extractor's silent drops.
Search, document and execute authenticated API calls across 700+ apps via one MCP server
Read, render, search, and manage reMarkable documents through MCP
Serves coding agents one canonical doc per query instead of rereading the repo — ~60% fewer tokens.