pdf-suite
Server Details
20 PDF MCP tools: repair, audit, merge, split, rotate, watermark, redact, forms, compress.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 20 tools
Most tools target a clearly distinct operation (merge, rotate, redact, repair, watermark, compare), and descriptions are specific enough to separate them. A few boundaries blur: pdf_split vs pdf_extract_pages both carve out page subsets, and pdf_compress, pdf_repair, and pdf_to_pdfa_archival all re-serialize/restructure the file, so an agent may hesitate on which to pick.
Every tool carries a uniform 'pdf_' prefix with snake_case and verb-led names, giving a highly predictable surface. Minor deviation in word order for conversion tools (pdf_to_markdown, pdf_from_html_text) and unusually long compound names (pdf_forms_inspect_and_fill, pdf_unlock_strip_restrictions) slightly break the clean verb_noun pattern.
20 tools sits at the upper edge but each maps to a genuinely distinct PDF operation spanning editing, conversion, security, and inspection, so most earn their place. It is somewhat heavy and a couple of tools (e.g. crop, protect_metadata) could arguably fold into others, but nothing feels redundant filler.
The surface covers the core PDF lifecycle broadly: merge/split/extract/remove pages, rotate/crop, watermark/number, compress/repair, redact, forms, compare, compliance, archival, and text/HTML/image conversion. Notable gaps remain: there is an unlock tool but no encrypt/password-protect counterpart, no image or page rendering export, and no precise metadata editing beyond scrubbing.
Available Tools
20 toolspdf_add_page_numbersCInspect
Stamp vector pagination or Bates numbers (e.g. "Page X of Y") onto every PDF page.
Inputs: prefix, inputPath, base64Data, outputPath, +1 more.
pdf_add_watermarkCInspect
Overlay a diagonal translucent vector text watermark (e.g. CONFIDENTIAL) across all pages of a PDF.
Inputs: opacity, inputPath, base64Data, outputPath, +1 more.
pdf_compareBInspect
Structurally compare two PDFs (page count, page dimensions, metadata, SHA-256, and extracted text tokens) to pinpoint differences.
Inputs: base64Data, secondBase64Data.
pdf_compliance_auditBInspect
Audit a PDF for hidden 3-Tr invisible text operators, OCG layers, active /JS, annotations, and metadata leaks, and optionally issue a SHA-256 Compliance Certificate PDF.
Inputs: filePath, filename, base64Data, outputPath, +1 more.
pdf_compressCInspect
Compact a PDF structurally by stripping unused objects, clearing XMP/metadata bloat, and enabling PDF 1.5 compressed Object Streams.
Inputs: inputPath, base64Data, outputPath.
pdf_crop_marginsCInspect
Trim uniform PDF CropBox margins (in points) across all pages while preserving vector content.
Inputs: marginPt, inputPath, base64Data, outputPath.
pdf_extract_pagesCInspect
Extract and reorder specific 1-based pages from a PDF into a new PDF file.
Inputs: pages, inputPath, base64Data, outputPath.
pdf_forms_inspect_and_fillCInspect
Inspect all interactive AcroForm fields in a PDF, optionally fill text/checkbox fields from JSON, and flatten form widgets.
Inputs: flatten, inputPath, base64Data, outputPath, +1 more.
pdf_from_html_textCInspect
Render HTML or plain text into a paginated vector PDF document using pdf-lib.
Inputs: text, title, outputPath.
pdf_from_imagesCInspect
Wrap one or more JPEG/PNG images (or fall back to an annotated vector page) into a clean PDF document.
Inputs: inputPath, base64Data, outputPath, imagesBase64.
pdf_mergeCInspect
Merge multiple base64-encoded PDF documents cleanly in exact page order via pdf-lib.
Inputs: base64Data, outputPath, documentsBase64.
pdf_protect_metadataCInspect
Audit PDF encryption state, scrub identifying Creator/Producer/Author metadata, and stamp deterministic integrity protection headers.
Inputs: inputPath, base64Data, outputPath, ownerLabel.
pdf_redact_termsCInspect
Scan PDF text streams for target terms or PII patterns (emails, SSNs, cards) and purge matching raw stream literals + metadata before re-saving.
Inputs: inputPath, base64Data, outputPath, redactTerms.
pdf_remove_pagesCInspect
Delete specified 1-based page numbers or ranges from a PDF document.
Inputs: inputPath, base64Data, outputPath, removePages.
pdf_repairCInspect
Scan damaged PDF binary objects and reconstruct broken/truncated XRef tables and trailers via pdf-lib.
Inputs: inputPath, base64Data, outputPath.
pdf_rotateAInspect
Permanently rotate all or selected pages of a PDF by 90, 180, or 270 degrees clockwise.
Inputs: angle, pages, inputPath, base64Data, +1 more.
pdf_splitCInspect
Split a PDF by page range or page chunk size into an extracted PDF slice plus per-range metadata.
Inputs: pages, inputPath, base64Data, outputPath.
pdf_to_markdownCInspect
Extract uncompressed PDF text operators (Tj/TJ) and document metadata into clean Markdown.
Inputs: filePath, base64Data.
pdf_to_pdfa_archivalCInspect
Normalize a PDF for long-term ISO-19005 PDF/A-like archival consistency by flattening forms, embedding standard fonts, and setting XMP/catalog timestamps.
Inputs: inputPath, base64Data, outputPath.
pdf_unlock_strip_restrictionsCInspect
Load owner-restricted PDFs (ignoreEncryption) and re-serialize clean unlocked pages without permission locks.
Inputs: inputPath, base64Data, outputPath.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Privacy-first PDF tools over MCP: merge, split, rotate, delete, compress, protect, inspect.
20 engineering MCP tools: 3D STL/G-code, ELF/WASM, Verilog/VCD, systemd/seccomp, PDF repair.
14 PDF tools: merge, split, compress, watermark, encrypt, organize, metadata, page extraction.
PDF tools + QR over MCP: merge, split, rotate, text, metadata, malicious-content scan.
Related MCP Servers
- AlicenseAqualityBmaintenanceA comprehensive MCP server with 37 tools for PDF operations including reading, searching, creating, merging, splitting, watermarking, form filling, and more, built on open-source libraries.3742 npm2MIT
- MIT

FynePDF MCP serverofficial
AlicenseNot gradedqualityCmaintenanceEnables MCP clients to compress, merge, split, convert, OCR, redact, sign, create, and read PDFs with AI-assisted summaries and data extraction, plus local file upload/download and URL imports. Supports file libraries, job tracking, documentation search, and authenticated access via OAuth or API keys.1MIT- AlicenseNot gradedqualityBmaintenanceEnables extracting text and metadata from local PDF files, inspecting page and file information, merging multiple PDFs, and splitting PDFs into single-page documents through MCP tools.74 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.