Mmcp.market

Topic

MCP servers for PDFs and documents

Turn PDFs, Word files and scans into something an agent can read.

Document servers look interchangeable and are not. The split is whether the file is parsed on your machine or uploaded to a hosted service, and since the files people want parsed are usually contracts, invoices and medical letters, that split matters more here than almost anywhere else.

Graded servers
197
Grade A
90
Run remotely
95
Reviewed by users
0

Before you install one

Three things that separate the servers here, none of which shows up in a description.

Local parse or upload?
OCR quality is the reason hosted services exist, and they are genuinely better on scans. But a hosted parser means the document goes to a third party. Decide that per document type, not once for the whole server.
Which directories can it open?
A read-this-file tool usually accepts any path the process can reach. Prefer one that takes a configured root, and give it a folder rather than a home directory.
A document can carry instructions.
Text inside a PDF becomes model input like any other text, and a document prepared by someone else can ask the agent to do things. This is worth remembering for anything that arrives by email.

Every listing below has a scan report saying what the server asks for and what it does with it. The rubric is on how we grade.

The PDF and document servers we would look at first

Reviewed servers rank first, then the ones with real adoption. At most two per publisher, so no account can fill the list. Nothing here is sponsored.

36 more, graded and ranked

  • 13
    PDF Merge Split Stamp Extract Text
    Merge, split, rotate, stamp and read PDFs from chat. Page ranges and watermarks, all on your machine
    C
  • 14
    PDF
    Merge, split, compress, unlock, organize, extract, fill forms and check PDFs — 12 local tools.
    C
  • 15
    pdfs.build
    Design, publish and render PDF templates with Typst. Full template lifecycle over MCP.
    B
  • 16
    PageProof
    PDF text by page with hashes. 0.005 USDC/Base via x402. No OCR. Check /health for readiness.
    C
  • 17
    Chart Generator & PDF Report from Any Dataset, CSV or JSON
    Turn rows into bar, line, pie and scatter chart images plus an optional PDF or HTML report.
    C
  • 18
    PDF Extractor: Bulk PDF to Text, Tables & Markdown from a CSV
    Extract text, tables and metadata from every PDF linked in a dataset, CSV or Google Sheet.
    C
  • 19
    PDF Text, Table and OCR Extractor
    PDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages.
    C
  • 20
    image-ocr
    Image URL → plain text OCR for bots. Free try then prepaid TEST. https://ocr.kymac.co
    C
  • 21
    pdf-text
    PDF URL → extracted text for bots. Free try then prepaid TEST. https://pdf.kymac.co
    C
  • 22
    Ebook File Check
    Run EPUBCheck for EPUB specification errors and compare two exports.
    C
  • 23
    PDF Agent by Nova (CIVAI)
    I create PDF documents from markdown, preview, then generate a downloadable file
    C
  • 24
    BrewMyPDF
    Render PDFs from templates you design once: list templates, check the data shape, preview, render.
    C
  • 25
    Invoice & Receipt OCR Extractor to Excel
    Invoice and receipt extractor: reads PDF and image invoices/receipts with AI, pulling date…
    C
  • 26
    PDF Toolkit
    Convert PDFs/images to Word, Excel, and Markdown. Split, merge, and watermark PDF files.
    C
  • 27
    Citra
    Local-first PDF evidence for agents: structure, tables, OCR, and citations. SDK · CLI · MCP.
    A
  • 28
    Ui.Vision MCP
    MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input
    C
  • 29
    Zoteus
    Zotero MCP server for Claude and ChatGPT: search, citations, safe writes, PDF passages and pages.
    A
  • 30
    Open Agreements
    Fill standard legal agreement templates (NDAs, SAFEs, NVCA docs, employment) as DOCX files.
    A
  • 31
    Immich Photo Manager
    Photo management for self-hosted Immich: search, albums, duplicates, faces, PDF reports. 94 tools.
    B
  • 32
    Docling MCP
    Convert PDFs and other documents to structured formats via Docling, for AI applications.
    A
  • 33
    Maket
    Compose branded visual documents with live preview, data collections, validation, and PDF export.
    A
  • 34
    Talkthrough
    Local MCP server: recordings or public video URLs into transcript, frames, OCR, wall-clock evidence.
    A
  • 35
    Nutrient DWS MCP Server
    Nutrient Processor + Data Extraction MCP: convert, OCR, sign, redact, and extract PDFs/Office docs.
    A
  • 36
    Endnote
    Search, cite, and read PDFs from your EndNote library in Claude Desktop
    A
  • 37
    MinerU
    MinerU document parsing API — PDFs, images, DOCX, PPTX with OCR and batch processing.
    A
  • 38
    Plonk
    MCP server for Plonk: macOS window zones, workspaces, keep-awake, screenshots and on-device OCR.
    A
  • 39
    KitchenSink4Word
    Word (.docx) MCP server: 221 operations, live editing, tracked changes, citations, mail merge.
    A
  • 40
    Paxa Labs
    Thai and English speech AI: TTS with local playback, transcription, translation to Thai, and OCR
    A
  • 41
    Templated
    Generate images, videos and PDFs from templates. Manage templates, folders, uploads and fonts.
    A
  • 42
    AILANG Parse
    Deterministic DOCX/PPTX/XLSX/PDF parser: track changes, comments, headers, footers, merged cells.
    A
  • 43
    Ezpzfile
    Local file tools for agents: documents, PDFs, images, QR codes. Nothing is uploaded.
    A
  • 44
    AgentMD
    Convert PDF, DOCX, HTML, and URLs to clean, LLM-ready markdown with tables preserved
    A
  • 45
    upAPI
    All public upAPI operations as MCP tools: web scraping, search, screenshots, PDF, OCR and more.
    A
  • 46
    Laddro Career
    Tailor resumes, generate cover letters, render CVs as PDF, and browse 22+ templates.
    A
  • 47
    Talonic
    Extract structured, schema-validated data from PDFs, scans, images, spreadsheets, and forms.
    A
  • 48
    MCP Server
    MCP server for the PDFGate API. Generate PDFs, manage documents and handle e-signatures.
    A

Or try them without installing any

Add the gateway once and your agent runs search "pdf", reads the grades, and calls the one it picks. Nothing to install per server, and an F-graded server cannot be reached through it.

Gateway docs
claude mcp add --transport http mcp-market https://gw.mcp.market/mcp

Related

MCP servers for RAGMCP servers for browser automationBest Productivity MCP serversAll topics