Skip to main content
Glama
1pdf

1pdf

by WendongAI

1pdf MCP Server

97 PDF tools for Claude, Cursor & Codex.

Give your AI assistant the power to merge, split, compress, convert, encrypt, add visible signatures, watermark, and analyze PDFs — all with natural language. Core tools run locally; professional document conversions can use optional local programs.

Official guide: 1pdf.best/mcp

Quick Start

OpenAI Codex

codex mcp add 1pdf -- npx -y onepdf-mcp-server

Verify with codex mcp list, restart Codex, then ask:

Use 1PDF to merge report1.pdf and report2.pdf.

Claude Code

claude mcp add 1pdf -- npx -y onepdf-mcp-server

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "1pdf": {
      "command": "npx",
      "args": ["-y", "onepdf-mcp-server"]
    }
  }
}

Cursor

Settings → MCP → Add Server:

Command: npx
Args: -y, onepdf-mcp-server

Windsurf

Settings → MCP → Add Server:

npx -y onepdf-mcp-server

Related MCP server: PDF Manipulation MCP Server

Check Available Capabilities

Ask your Agent to call system_status before workflows that use Office, MOBI, DjVu, XPS, Ghostscript, or PDF/A conversion.

The status response reports:

  • the 1PDF MCP and Node versions;

  • detected optional programs and versions;

  • tools enabled by each program;

  • platform-specific installation instructions for missing programs.

Core PDF tools run with the npm package. Professional document conversion uses optional local programs. Missing dependencies return MISSING_DEPENDENCY; 1PDF does not report a successful conversion when a required program is missing.

Capability Boundaries

  • sign_pdf adds a visible signature appearance. It does not provide certificate-backed authenticity.

  • pdf_to_pdfa and font_to_outline require Ghostscript. PDF/A conversion can optionally require independent veraPDF validation with validate: true.

  • ocg_manager accurately lists Optional Content Groups. Persisting layer visibility is not available yet and returns a structured failure without writing a copied output.

  • deskew_pdf automatically detects and corrects page tilt locally. The corrected output is rasterized, so selectable text and vector elements become images; use OCR afterward when searchable text is required.

  • compress uses a lossless structural rewrite at high quality, Ghostscript image resampling at low quality, and the best available medium-quality path. Its result reports when an already-compact PDF did not become smaller.

What You Can Do

Once installed, just talk to your AI assistant naturally:

"Merge report1.pdf and report2.pdf"
"Split this PDF into pages 1-3 and 5"
"Encrypt this PDF with password mypass123"
"Add a DRAFT watermark to this PDF"
"Convert these JPG images to a single PDF"
"Extract all tables from this PDF"
"Convert this Markdown file to PDF"

All 97 Tools

Organize & Manage (12)

merge · split · extract_pages · delete_pages · sort_pages · reverse_pages · add_blank_page · rotate · alternate_merge · view_metadata · edit_metadata · page_dimensions

Edit & Annotate (7)

watermark · page_number · add_header_footer · add_stamps · crop_pdf · flatten_pdf · bates_number_pdf

Optimize & Security (6)

compress · encrypt · decrypt · redact_pdf · remove_metadata · invert_colors

Convert — Image → PDF (9)

image_to_pdf · jpg_to_pdf · png_to_pdf · webp_to_pdf · bmp_to_pdf · tiff_to_pdf · svg_to_pdf · heic_to_pdf · psd_to_pdf

Convert — PDF → Image (6)

pdf_to_png · pdf_to_jpg · pdf_to_webp · pdf_to_bmp · pdf_to_tiff · pdf_to_zip

Document Conversion (10)

markdown_to_pdf · pdf_to_markdown · txt_to_pdf · json_to_pdf · email_to_pdf · cbz_to_pdf · epub_to_pdf · rtf_to_pdf · pdf_to_greyscale · pdf_to_pdfa

Page Layout (7)

divide_pages · combine_single_page · nup_pdf · pdf_booklet · posterize_pdf · grid_combine · fix_page_size

Analysis & Info (9)

pdf_reader · get_page_text · pdf_search · get_pdf_chunks · compare_pdfs · remove_blank_pages · pdf_to_json · extract_tables · table_of_contents

Annotations & Metadata (6)

edit_bookmarks · extract_attachments · remove_annotations · background_color · change_permissions · ocg_manager

Optimize (4)

repair_pdf · linearize_pdf · sanitize_pdf · remove_restrictions

Forms & Signing (3)

sign_pdf · form_filler · form_creator

AI Tools (3)

ai_summarize · ai_chat_with_pdf · ai_extract_info

Specialized (6)

deskew_pdf · rasterize_pdf · extract_images · add_attachments · edit_attachments · font_to_outline

External Tools (9) — require LibreOffice/Calibre/DjVuLibre

word_to_pdf · excel_to_pdf · powerpoint_to_pdf · pdf_to_docx · pdf_to_excel · pdf_to_ppt · mobi_to_pdf · djvu_to_pdf · xps_to_pdf

Core tools process files locally. Nine document-conversion tools use optional LibreOffice, Calibre, or DjVuLibre installations; system_status reports their availability before an Agent starts a workflow.

Requirements

  • Node.js 20.9+

  • Claude Desktop, Cursor, Windsurf, or Claude Code

  • Optional: LibreOffice, Calibre, DjVuLibre, Ghostscript, and veraPDF for specialized conversions and validation

Development

git clone https://github.com/WendongAI/onepdf-mcp-server.git
cd onepdf-mcp-server
npm install
npm run build          # TypeScript build
npm test               # native tools + quality + runtime + MCP E2E
npm run test:package   # install and start the packed npm tarball

License

MIT © 1pdf

Available Tools

98 tools
add_attachmentsB

Attach files to a PDF as embedded attachments.

Inputs: file (required), attachments (required), output_name.

add_blank_pageB

Insert blank pages into a PDF at a specific position.

Inputs: file (required), count, width, height, +2 more.

add_stampsC

Add a text stamp to a PDF at a specific position.

Inputs: file (required), text (required), color, position, +2 more.

ai_chat_with_pdfA

Ask a question about a PDF and get an answer based on its text content.

Inputs: file (required), question (required).

ai_extract_infoC

Extract structured information (entities, dates, numbers) from a PDF.

Inputs: file (required).

ai_summarizeB

Extract and summarize the text content of a PDF (returns key text).

Inputs: file (required).

alternate_mergeA

Interleave pages from multiple PDFs. Takes page 1 from each file, then page 2, etc.

Inputs: files (required), output_name.

background_colorA

Set a background color for all pages of a PDF.

Inputs: file (required), color, output_name.

bates_number_pdfB

Add continuous, zero-padded Bates identifiers for legal and audit document production.

Inputs: file (required), start, digits, margin, +5 more.

bmp_to_pdfA

Convert a BMP image to a PDF page.

Inputs: file (required), output_name.

cbz_to_pdfA

Convert a comic book archive (.cbz) to a PDF (one page per image).

Inputs: file (required), output_name.

change_permissionsB

Set PDF access permissions (print, copy, edit).

Inputs: file (required), allow_copy, allow_edit, allow_print, +1 more.

combine_single_pageC

Combine all pages onto a single page in a grid layout.

Inputs: file (required), cols, rows, output_name.

compare_pdfsA

Compare two PDFs and report differences in page count, text, and size.

Inputs: file1 (required), file2 (required).

compressB

Compress a PDF to reduce file size.

Inputs: file (required), quality, output_name.

crop_pdfA

Crop pages by specifying margins to remove from each side (in points).

Inputs: file (required), top, left, right, +2 more.

decryptB

Decrypt a password-protected PDF (removes password).

Inputs: file (required), password (required), output_name.

delete_pagesA

Delete specific pages from a PDF. E.g. pages "2,4-6" removes pages 2,4,5,6.

Inputs: file (required), pages (required), output_name.

deskew_pdfA

Automatically detect and correct tilted scanned PDF pages. Output pages are rasterized.

Inputs: file (required), dpi, max_angle, output_name.

divide_pagesA

Split each page into two pages (horizontally or vertically).

Inputs: file (required), direction, output_name.

djvu_to_pdfA

Convert a DjVu document to PDF. Requires DjVuLibre.

Inputs: file (required), output_name.

edit_attachmentsB

List or remove file attachments in a PDF.

Inputs: file (required), action, remove, output_name.

edit_bookmarksC

Add or replace bookmarks (outline/TOC sidebar) in a PDF.

Inputs: file (required), bookmarks (required), output_name.

edit_metadataB

Edit PDF metadata fields (title, author, subject, keywords).

Inputs: file (required), title, author, subject, +2 more.

email_to_pdfA

Convert an email file (.eml) to a PDF with headers and body.

Inputs: file (required), output_name.

encryptA

Encrypt a PDF with AES-256 password protection.

Inputs: file (required), password (required), output_name.

epub_to_pdfA

Convert an EPUB ebook to a PDF (extracts text content).

Inputs: file (required), output_name.

excel_to_pdfA

Convert an Excel spreadsheet (.xls/.xlsx) to PDF. Requires LibreOffice.

Inputs: file (required), output_name.

extract_attachmentsA

Extract all file attachments embedded in a PDF.

Inputs: file (required), output_dir.

extract_imagesA

Extract all embedded images from a PDF as separate files.

Inputs: file (required), output_dir.

extract_pagesB

Extract specific pages from a PDF into a new document.

Inputs: file (required), pages (required), output_name.

extract_tablesB

Extract tables from a PDF. Returns table data as arrays.

Inputs: file (required).

fix_page_sizeA

Resize all pages to a specific width and height (in points).

Inputs: file (required), width, height, output_name.

flatten_pdfA

Flatten form fields and annotations into the page content (makes them non-editable).

Inputs: file (required), output_name.

font_to_outlineA

Convert all fonts in a PDF to vector outlines (prevents font substitution).

Inputs: file (required), output_name.

form_creatorB

Add form fields (text inputs, checkboxes) to a PDF.

Inputs: file (required), fields (required), output_name.

form_fillerC

Fill in form fields in a PDF with provided values.

Inputs: file (required), fields (required), output_name.

get_page_textA

Read full text from selected PDF pages without loading the entire document into context.

Inputs: file (required), pages, max_chars_per_page.

get_pdf_chunksA

Read PDF text in stable overlapping chunks for long-document Agent workflows.

Inputs: file (required), overlap, chunk_size, max_chunks, +1 more.

grid_combineC

Combine multiple PDFs side-by-side on single pages in a grid.

Inputs: files (required), cols, output_name.

heic_to_pdfA

Convert a HEIC/HEIF photo (iPhone format) to a PDF page.

Inputs: file (required), output_name.

image_to_pdfB

Convert one or more images (JPG/PNG) into a multi-page PDF.

Inputs: files (required), page_size, output_name.

invert_colorsA

Invert the colors of all pages (useful for dark mode printing).

Inputs: file (required), output_name.

jpg_to_pdfB

Convert a single JPG/JPEG image to a PDF page.

Inputs: file (required), output_name.

json_to_pdfB

Convert a JSON file to a formatted PDF document.

Inputs: file (required), output_name.

linearize_pdfB

Optimize a PDF for fast web viewing (linearized/Web Optimized).

Inputs: file (required), output_name.

markdown_to_pdfB

Convert a Markdown (.md) file to a formatted PDF.

Inputs: file (required), output_name.

mergeA

Combine multiple PDF files into a single document. Preserves all pages in order.

Inputs: files (required), output_name.

mobi_to_pdfA

Convert a Kindle ebook (.mobi) to PDF. Requires Calibre.

Inputs: file (required), output_name.

nup_pdfC

Place N pages per sheet (2-up, 4-up, etc.).

Inputs: n (required), file (required), output_name.

ocg_managerA

Inspect Optional Content Groups (layers); changing visibility is not yet available.

Inputs: file (required), action (required), layer, output_name.

page_dimensionsA

Get page dimensions (width × height in points) for all pages in a PDF.

Inputs: file (required).

page_numberB

Add page numbers to each page of a PDF.

Inputs: file (required), start, format, position, +1 more.

pdf_bookletB

Arrange pages for booklet printing (signatures).

Inputs: file (required), output_name.

pdf_readerA

Extract all text content from a PDF. Returns the text of each page.

Inputs: file (required).

pdf_to_bmpB

Render PDF pages as BMP images.

Inputs: file (required), dpi, pages, output_dir.

pdf_to_docxA

Convert a PDF to a Word document (.docx). Requires LibreOffice.

Inputs: file (required), output_name.

pdf_to_excelB

Convert a PDF to an Excel spreadsheet (.xlsx). Requires LibreOffice.

Inputs: file (required), output_name.

pdf_to_greyscaleB

Convert all pages of a PDF to greyscale.

Inputs: file (required), output_name.

pdf_to_jpgB

Render PDF pages as JPEG images.

Inputs: file (required), dpi, pages, output_dir.

pdf_to_jsonA

Export PDF structure (pages, text, metadata) as a JSON file.

Inputs: file (required), output_name.

pdf_to_markdownA

Extract PDF text as page-labelled Markdown with heading and simple list detection.

Inputs: file (required), output_name.

pdf_to_pdfaB

Convert a PDF to PDF/A archival format.

Inputs: file (required), level, validate, output_name.

pdf_to_pngB

Render PDF pages as PNG images.

Inputs: file (required), dpi, pages, output_dir.

pdf_to_pptA

Convert a PDF to a PowerPoint presentation (.pptx). Requires LibreOffice.

Inputs: file (required), output_name.

pdf_to_tiffB

Render PDF pages as TIFF images.

Inputs: file (required), dpi, pages, output_dir.

pdf_to_webpB

Render PDF pages as WebP images.

Inputs: file (required), dpi, pages, output_dir.

pdf_to_zipA

Extract all pages as images and bundle them into a ZIP archive.

Inputs: file (required), output_name.

png_to_pdfA

Convert a single PNG image to a PDF page.

Inputs: file (required), output_name.

posterize_pdfA

Split each page into a grid of tiles for poster printing.

Inputs: file (required), cols, rows, output_name.

powerpoint_to_pdfB

Convert a PowerPoint presentation (.ppt/.pptx) to PDF. Requires LibreOffice.

Inputs: file (required), output_name.

psd_to_pdfA

Convert a Photoshop PSD file to a PDF (flattens all layers).

Inputs: file (required), output_name.

rasterize_pdfC

Convert PDF pages to images and back (rasterizes vector content).

Inputs: file (required), dpi, output_name.

redact_pdfA

Permanently redact exact text values and rasterize pages so the source text cannot be recovered.

Inputs: file (required), terms (required), dpi, output_name, +1 more.

remove_annotationsA

Remove all annotations (comments, highlights, etc.) from a PDF.

Inputs: file (required), output_name.

remove_blank_pagesB

Remove blank or near-blank pages from a PDF.

Inputs: file (required), output_name.

remove_metadataB

Strip all metadata (title, author, etc.) from a PDF.

Inputs: file (required), output_name.

remove_restrictionsB

Remove all access restrictions from a PDF.

Inputs: file (required), output_name.

repair_pdfB

Repair a corrupted PDF by reloading and re-saving with pdf-lib.

Inputs: file (required), output_name.

reverse_pagesA

Reverse the page order of a PDF (last page becomes first).

Inputs: file (required), output_name.

rotateB

Rotate pages in a PDF by 90, 180, or 270 degrees.

Inputs: file (required), degrees (required), pages, output_name.

rtf_to_pdfB

Convert an RTF document to a PDF.

Inputs: file (required), output_name.

sanitize_pdfA

Sanitize a PDF by removing JavaScript, embedded files, and metadata.

Inputs: file (required), output_name.

sign_pdfA

Add a visible text signature appearance to a PDF; no certificate-backed authenticity is provided.

Inputs: file (required), name (required), x, y, +2 more.

sort_pagesA

Reorder pages in a PDF by custom order. E.g. order [3,1,2] puts page 3 first.

Inputs: file (required), order (required), output_name.

splitA

Split a PDF into separate files by page range. E.g. pages "1-3,5" extracts pages 1,2,3,5.

Inputs: file (required), pages (required), output_name.

svg_to_pdfA

Convert an SVG vector image to a PDF page.

Inputs: file (required), output_name.

system_statusA

Report 1PDF MCP version, platform, optional dependencies, and which tools are currently available.

Inputs: refresh.

table_of_contentsB

Add a table of contents page to a PDF with clickable entries.

Inputs: file (required), entries (required), output_name.

tiff_to_pdfB

Convert a TIFF image to a PDF page.

Inputs: file (required), output_name.

txt_to_pdfA

Convert a plain text (.txt) file to a PDF.

Inputs: file (required), font_size, output_name.

view_metadataA

View PDF metadata: title, author, subject, keywords, creator, page count.

Inputs: file (required).

watermarkA

Add a text watermark overlay to all pages of a PDF.

Inputs: file (required), text (required), opacity, rotation, +1 more.

webp_to_pdfA

Convert a WebP image to a PDF page.

Inputs: file (required), output_name.

word_to_pdfA

Convert a Word document (.doc/.docx) to PDF. Requires LibreOffice.

Inputs: file (required), output_name.

xps_to_pdfA

Convert an XPS document to PDF. Requires LibreOffice.

Inputs: file (required), output_name.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.9/5.0

    Scored across 98 tools

    Disambiguation2/5

    Several tool groups are easily confused: pdf_to_tiff and pdf_to_zip both render pages as images; combine_single_page, nup_pdf, and grid_combine all create grid-style page layouts; watermark, add_stamps, add_header_footer, page_number, and bates_number_pdf all place text overlays; and the AI tools overlap in purpose. With 98 tools, an agent will frequently struggle to select the right one.

    Naming Consistency3/5

    The X_to_pdf and pdf_to_X patterns are consistent, and everything uses snake_case, but many tools break the pattern with bare verbs (merge, split, rotate, compress), nouns (pdf_reader, page_dimensions, system_status), and odd names (nup_pdf, ocg_manager, form_filler). The naming is readable but mixes several conventions.

    Tool Count1/5

    98 tools is an extreme count for a single MCP server. While PDF manipulation is broad, this is a monolithic all-in-one utility with dozens of marginal variants (e.g. 9 image-to-PDF converters), which creates unnecessary selection overhead and tool bloat.

    Completeness4/5

    The server covers an unusually wide range of PDF workflows: conversion, merging/splitting, page manipulation, metadata, security, forms, attachments, bookmarks, redaction, and AI-assisted extraction. Minor gaps exist, such as OCR, true digital signatures, annotation creation, and HTML-to-PDF conversion, but most core PDF tasks are represented.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents and users to process documents through natural language, supporting PDF operations like text extraction, redaction, splitting, form filling, annotations, and content search.
      60 npm
      62
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI-powered PDF manipulation through natural language commands, integrating with Claude to perform operations like merging, splitting, encrypting, optimizing, and analyzing PDFs.
      16
      -
    • A
      license
      B
      quality
      D
      maintenance
      Enables AI assistants to perform a wide range of PDF processing tasks, including conversion, editing, merging, splitting, OCR, barcode/QR code generation and reading, AI-powered data extraction, and image processing, through the PDF4me API.
      92
      MIT