PaperPilot MCP
PaperPilot MCP is a local, privacy-preserving PDF/document toolkit exposed as MCP tools for AI agents.
Core PDF editing: merge, split, extract/delete/reorder/rotate/crop/burst/compress, add page numbers/headers/footers, watermark, Bates numbering, bookmarks, annotations, render to images.
Conversions: PDF to/from Word, Excel, PowerPoint, Markdown, HTML, JSON, EPUB, images; HTML/Markdown/Excel/JSON/images to PDF; Office to Markdown/text and legacy Office modernization.
AI/RAG/search: semantic and workspace search, structure-aware chunking/RAG chunks, text/pattern extraction, PDF type classification, natural-language
cli_askplanning.Forms: read/fill AcroForm PDFs, create fields, flatten, and batch fill from CSV/JSON with receipts.
Security/privacy: PII scanning, permanent redaction, encrypt/decrypt, permissions, sanitize, hash/validate, signature validation, timestamping, remove signatures.
Workflow automation: declarative recipes/workflows, preset workflows, one-shot
recipe_run, hot-folder watcher start/stop/list, execution receipt list/get.Specialty PDF ops: booklet/N-up imposition, page scaling, stamps/overlays, auto-rotate, stitching, attachments, PDF/A, repair, linearize, comic archives, split by outline, alternating merge, posterize, stream dedup, split scanned books, compare PDFs, OCR.
Office/spreadsheet tools: extract text/Markdown from Office docs, Excel to CSV/JSON.
File handling: local path inputs/outputs; supports batch/automated pipelines and persists receipts without storing PDF contents or recipe parameters.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
PaperPilot
PDF tools for your AI agent — and for you. Pure Rust. Runs locally. Files never leave your machine.

Try it in your browser → · Download · Contributing · Roadmap
PaperPilot is a PDF and document toolkit written in Rust. The same engine runs as:
Surface | Use it for |
MCP server | Give Codex, Claude Code, Gemini CLI, Cursor, Claude Desktop, or any MCP client instant document superpowers |
CLI | High-speed batch workflows and automated terminal pipelines |
Browser Extension | In-tab right-click actions on web/arXiv PDFs, clean article capture, and WASM toolkit |
Browser (WASM) | Zero-install web tools; files are processed in browser memory, nothing is uploaded |
Desktop app | Tauri + Svelte 5 GUI with interactive canvas, viewer, and pipeline builder |
Local REST API | Call it from Python, Node.js, n8n, LangChain, or LlamaIndex at |
No Chromium, no C++ runtime, no cloud calls.
Self-Healing System Diagnostics
Verify your environment, gateway port, temp storage, and OCR models with one command:
paperpilot doctor
# PaperPilot System Diagnostics (v0.7.0)
# ==================================================
# Status: Healthy
# [✓] Temp Directory: /tmp (writable & ephemeral cleanup verified)
# [✓] Gateway Port: 7823 available
# [✓] OCR Models: models/ocr/ppocrv4 (det.onnx, rec.onnx found)
# [✓] Disk Space: > 5 GB availableOpen-WebUI integration (source builds): use the local gateway as a PDF-only Tika-compatible extraction server. See the Open-WebUI setup guide.
Related MCP server: opendocswork-mcp
Quick start
1. Use it with your AI / Coding Agent (5-Second MCP Setup)
No manual build or binary download required! Run instantly via npx:
# Test MCP server directly
npx -y @usepaperpilot/mcp --helpAdd to Claude Desktop (claude_desktop_config.json), Cursor (cursor_mcp_config.json), Windsurf, or Zed:
{
"mcpServers": {
"paperpilot": {
"command": "npx",
"args": ["-y", "@usepaperpilot/mcp"]
}
}
}Or if using the precompiled native binary, download paperpilot-mcp from Releases or use client config generators:
paperpilot-mcp --client-config cursor
# Also: claude-desktop, claude-code, codex, kimi-code, piRestart Claude and try: "Merge these two PDFs and compress the result."
2. Use the CLI
# Semantic Chunking for AI Agents & RAG (Spec 159)
paperpilot pdf-chunk --input contract.pdf --target-tokens 500 --overlap 50 --json
# Merge multiple documents
paperpilot merge --inputs doc1.pdf doc2.pdf --output merged.pdf
# High-efficiency compression
paperpilot compress --input in.pdf --quality 75 --output compressed.pdf
# Search pattern or keywords across document pages
paperpilot search --input in.pdf --query "Invoice" --json
# Rotate pages 1, 3–5 by 90°
paperpilot rotate --input in.pdf --pages 1,3-5 --angle 90 --output out.pdf3. Use it in the browser & extension
Web App: Go to usepaperpilot.com for zero-install client-side WebAssembly tools.
Companion Extension: Load the Manifest V3 browser extension from
apps/extensionfor in-tab context menus, right-click PDF actions, and clean web article capture.
4. Build from source
git clone https://github.com/KrushnaVardhanReddy/PaperPilot.git
cd PaperPilot
cargo build --release -p paperpilot-cli -p paperpilot-mcp -p paperpilot-gatewayDesktop app:
cd apps/desktop && pnpm install && pnpm tauri devRequires Rust 1.75+, Node.js, and pnpm.
What it can do (92 Tools Across 5 Interfaces)
AI Agent Intelligence, Semantic Search & Workflows:
document_workflow&recipe_run: Declarative.ppflowDAG workflows with step dependencies, conditions, and cryptographic audit receipts.workspace_search&semantic_search: Multi-format recursive workspace search (.pdf,.docx,.xlsx,.md,.txt,.csv,.json) and normalized vector chunk retrieval.cli_ask: Natural language intent planner and instant execution agent.pdf_chunk&pdf_rag_chunks: Structure-aware semantic chunker respecting#/##headings,\n\nparagraphs, and keeping Markdown tables atomic.pdf_search&pdf_extract_patterns: High-precision regex and pattern extraction for invoices, order IDs, and legal identifiers.pdf_classify_type: Automatic document categorization (invoices, receipts, legal briefs, tax filings, research papers).
Core Layout, Bates Numbering & Imposition:
pdf_bates: Standard legal discovery Bates numbering across 6 customizable anchor positions.Merge, split, rotate, delete pages, reorder pages, extract pages, booklet imposition, N-up grid, and multi-sheet poster tile slicing (
pdf_posterize).Interactive forms: read form fields (
pdf_read_form), fill (pdf_fill_form,batch_fill), create form fields (pdf_create_form_field), and flatten (pdf_flatten).Digital signatures & timestamps (
pdf_sign,pdf_validate_signatures,pdf_timestamp), bookmarks (pdf_bookmarks), and crop/scale (pdf_crop,pdf_scale_pages).
Office & Cross-Format Transformations:
Bidirectional PDF ⇄ Word (
pdf_to_docx,pdf_convert_markdown).Bidirectional PDF ⇄ Excel (
pdf_to_xlsx,pdf_convert_excel,excel_to_csv,excel_to_json).EPUB eBooks (
pdf_to_epub), PowerPoint slides (pdf_to_pptx), HTML (pdf_to_html,pdf_convert_html), and JSON ASTs (pdf_to_json,json_to_pdf).Legacy Office modernization (
office_modernize_legacy,office_extract_text,office_to_markdown).
OCR & Document Vision:
Neural PP-OCRv4 detection & recognition via
rtenandocrs(det.onnx + rec.onnx).Searchable OCR text layer injection, auto-rotation (
pdf_auto_rotate), page rendering (pdf_render), and blank page removal (pdf_remove_blank).
Security & PII Redaction:
Automated PII scanning (
document_pii_scan) detecting SSNs, credit cards, emails, phone numbers, and IBANs.Permanent redaction (
pdf_redact) via coordinates, keywords, regex, or structured JSON datasets.Cryptographic validation & hashing (
pdf_validate,pdf_hash), encryption/decryption (pdf_encrypt,pdf_decrypt), permissions bitmask (pdf_change_permissions), and sanitization (pdf_sanitize).
Zero-Copy High Performance Engine:
Zero-copy memory-mapped I/O (
DocumentSourceviamemmap2) for files $\ge 10\text{ MB}$, keeping resident memory flat (< 100 MB) during search, chunking, and PII scanning of 500+ page documents.Universal streaming page batching (
PageBatchIterator) to prevent OOM errors.
Why another PDF tool?
Private by default. Everything runs locally or in your browser tab.
Agent-ready. MCP support is first-class, not an afterthought.
One engine, many surfaces. CLI, MCP, REST, WASM, and desktop share the same Rust core, so behavior is consistent.
Small and dependency-light. Pure Rust, built on
lopdf,pdf_oxide,rten, and friends.
Benchmarks
Run cargo bench --workspace to reproduce. Methodology and results: SYSTEM_BENCHMARK_REPORT.md.
Architecture
Desktop (Tauri) · CLI · REST (Axum) · MCP (stdio) · WASM (browser / edge)
│
Rust core workspace
paperpilot-core · paperpilot-pdf · paperpilot-nlp · paperpilot-gateway
paperpilot-mcp · paperpilot-wasm · paperpilot-storageEmbed in your own site
<script src="https://usepaperpilot.com/embed.js" data-tools="merge,compress,ocr"></script>
<div id="paperpilot-widget"></div>Local REST API & Document Ingestion
paperpilot serve --port 7823
# Standard PDF Operations (JSON & multipart)
curl -X POST http://localhost:7823/api/v1/pdf/merge \
-H "Content-Type: application/json" \
-d '{"inputs": ["a.pdf", "b.pdf"], "output": "out.pdf"}'
# Open-WebUI & Tika In-Memory Ingestion (sub-5ms)
curl -X PUT http://localhost:7823/tika/text \
-H "Content-Type: application/pdf" \
--data-binary @sample.pdfInteractive Swagger OpenAPI docs at http://localhost:7823/swagger-ui.
Security & Supply Chain Integrity
PaperPilot processes sensitive, proprietary, and personal documents on-device without cloud dependencies. We maintain rigorous software supply chain and security compliance:
OpenSSF Scorecard: 8.2 / 10
Token Permissions: 100% scoped to
permissions: read-all(principle of least privilege).SAST & Secret Gate: Continuous Semgrep OSS and Trivy security audits gating all commits.
Dependency Hardening: All third-party GitHub Actions pinned to immutable 40-character commit SHAs.
Responsible Disclosure: See
SECURITY.mdfor our vulnerability disclosure policy and 48-hour response SLA.
Contributing & Community
Issues and PRs are welcome. Good first contributions: bug reports with a sample PDF, new tool requests, and docs fixes.
Special thanks to all community members and contributors recognized in CONTRIBUTORS.md.
License
Community Edition (this repo): Apache 2.0. It includes the CLI, MCP server, REST gateway, WASM engine, and desktop app.
An Enterprise Edition (SSO, RBAC, audit logs, DLP) is developed separately.
Available Tools
95 toolsbatch_fillA
Fill a local AcroForm PDF from a CSV/JSON path or inline JSON records; returns per-row results and a persisted receipt. Flattens by default and never overwrites outputs.
Inputs: template (required), output_dir (required), data, date, +4 more.
cli_askC
AI Document Assistant: Interprets natural language instructions and executes document plans via offline NLP.
Inputs: prompt (required), input, output, dry_run.
cli_fill_batchC
Automated batch AcroForm fill engine generating populated PDFs and machine-readable receipts.
Inputs: template (required), output_dir (required), data, date, +4 more.
document_pii_scanC
Scan document for PII and sensitive information [Input: .pdf | Output: JSON report]
Inputs: input (required), output, scan_ssn, scan_iban, +3 more.
document_workflowC
Execute a declarative multi-step document workflow pipeline
Inputs: input (required), output (required), preset, recipe, +1 more.
excel_to_csvB
Export Excel spreadsheet (.xlsx/.xls) sheet to standard RFC 4180 CSV.
Inputs: input (required), output (required), sheet.
excel_to_jsonB
Ingest Excel spreadsheet (.xlsx/.xls) into structured JSON with cell type preservation.
Inputs: input (required), sheet, output, has_headers.
execution_receipt_getC
Query durable local workflow, batch or watcher execution receipts; no PDF contents or recipe parameters are stored
Inputs: directory (required), receipt_id (required), limit.
execution_receipt_listB
Query durable local workflow, batch or watcher execution receipts; no PDF contents or recipe parameters are stored
Inputs: directory (required), limit, receipt_id.
html_to_pdfC
Convert HTML to styled PDF
Inputs: input (required), output (required), preset, page_size, +2 more.
img_to_pdfB
Converts image(s) to a PDF document. [Input: JPG/PNG/WebP images | Output: PDF (.pdf)]
Inputs: inputs (required), output (required).
json_to_pdfC
Synthesizes a publication-ready PDF document from structured JSON text and embedded images
Inputs: input (required), output (required), preset, page_size, +2 more.
list_workflowsA
List all available preset document workflows
Inputs: no named parameters.
md_to_pdfC
Convert Markdown to styled PDF
Inputs: input (required), output (required), preset, page_size, +2 more.
office_extract_textB
Extract text content from Microsoft Office documents. [Input: Office (.docx, .xlsx, .pptx) | Output: Plain Text (.txt)]
Inputs: input (required), output.
office_modernize_legacyC
Modernize legacy Office document. [Input: Legacy Office (.doc, .xls, .ppt) | Output: Modern Office (.docx, .xlsx, .pptx)]
Inputs: input (required), output (required).
office_to_markdownB
Convert Office document to Markdown. [Input: Office (.docx, .xlsx, .pptx) | Output: Markdown (.md)]
Inputs: input (required), output (required).
pdf_annotateC
Applies annotations to a PDF document. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), output (required), regex, rules, +2 more.
pdf_attachmentsC
PDF Portfolio Attachments: Inspect, extract, or embed file attachments into PDF portfolios. [Input: .pdf | Output: .json]
Inputs: input (required), output (required), action, file_name, +2 more.
pdf_auto_rotateB
Auto Upright Orientation: Heuristically detect text baseline and rotation angle to automatically upright pages. [Input: .pdf | Output: .pdf]
Inputs: input (required), output (required).
pdf_batesC
Adds Bates numbering to a PDF. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), output (required), prefix (required), padding (required), +2 more.
pdf_bookletB
Booklet Imposition: Reorder and impose pages for 2-sided folding booklet printing. [Input: .pdf | Output: .pdf]
Inputs: input (required), output (required).
pdf_bookmarksC
Handles bookmarks in a PDF. [Input: PDF (.pdf) | Output: JSON array]
Inputs: input (required), output (required).
pdf_burstB
Bursts a PDF into individual files, returning the path of each.
Inputs: input (required), output_dir (required).
pdf_change_permissionsC
Modify PDF Permissions: Configure user and owner permissions for printing, copying, and modification. [Input: .pdf | Output: .pdf]
Inputs: input (required), output (required).
pdf_chunkB
Structure-aware semantic chunking with dynamic overlap for AI agents and LLM context windows. [Input: PDF (.pdf) | Output: JSON]
Inputs: input (required), output, target_tokens, overlap_tokens, +2 more.
pdf_classify_typeC
Classifies the PDF document type based on heuristics.
Inputs: input (required).
pdf_comic_archiveC
Comic Archive Conversion: Convert between PDF documents and comic book archive formats (CBZ/CBR). [Input: .pdf | Output: .cbr]
Inputs: input (required), output (required).
pdf_compareC
Compares two PDFs. [Input: 2 PDFs | Output: JSON report (.json)]
Inputs: input_a (required), input_b (required), file1, file2, +3 more.
pdf_compressB
Compresses a PDF to reduce file size. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), output (required), quality.
pdf_convert_excelC
Convert Excel/CSV to styled PDF via semantic HTML
Inputs: input (required), output (required), preset, page_size, +2 more.
pdf_convert_htmlC
Convert HTML to styled PDF
Inputs: input (required), output (required), preset, page_size, +2 more.
pdf_convert_markdownC
Convert Markdown to styled PDF
Inputs: input (required), output (required), preset, page_size, +2 more.
pdf_create_form_fieldC
Add a new form field (text or checkbox) to a PDF page.
Inputs: x (required), y (required), page (required), input (required), +5 more.
pdf_cropC
Crops pages to specific dimensions. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: box (required), input (required), output (required).
pdf_decryptC
Decrypts a PDF using the provided password. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), output (required), password (required).
pdf_dedup_streamsC
Lossless Stream Deduplication: Lossless hash-based indirect object stream deduplication & CMYK-safe image compression [Input: .pdf | Output: .pdf]
Inputs: input (required), output (required).
pdf_delete_pagesB
Deletes specific pages. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), pages (required), output (required).
pdf_encryptC
Encrypts a PDF with a user password. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), output (required), password (required).
pdf_extract_imagesC
Extract raster images from a PDF. [Input: PDF (.pdf) | Output: PNG/JPEG images]
Inputs: input (required), output_dir (required).
pdf_extract_pagesB
Extracts specific pages into a new PDF. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), pages (required), output (required).
pdf_extract_patternsC
Extract Keywords & Patterns: Scan document for custom keywords and regex patterns with match contexts [Input: .pdf | Output: .json]
Inputs: input (required), output, keywords, patterns, +2 more.
pdf_extract_tablesC
Extract tabular data from PDF into JSON or CSV
Inputs: input (required), format, output.
pdf_extract_textC
Extracts raw text from a PDF. [Input: PDF (.pdf) | Output: Plain Text (.txt)]
Inputs: input (required), output (required), pages.
pdf_fill_formC
Fill AcroForm fields in a PDF. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), output (required), values (required).
pdf_flattenB
Flattens a PDF by merging interactive elements into the page content.
Inputs: input (required), output (required).
pdf_hashB
Calculates integrity hash for a PDF. [Input: PDF (.pdf) | Output: Plain Text (.txt)]
Inputs: input (required).
pdf_images_to_pdfA
Converts a list of images to a PDF. [Input: JPG/PNG/WebP images | Output: PDF (.pdf)]
Inputs: inputs (required), output (required).
pdf_infoC
Get basic PDF information like page_count. [Input: PDF (.pdf) | Output: JSON object]
Inputs: input (required).
pdf_linearizeB
Linearizes a PDF for fast web view. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), output (required).
pdf_mergeB
Merges multiple PDFs into one. [Input: 2+ PDFs | Output: PDF (.pdf)]
Inputs: inputs (required), output (required).
pdf_merge_alternateC
Alternating PDF Merge: Interleave pages from two PDF documents. [Input: .pdf | Output: .pdf]
Inputs: output (required), input_a (required), input_b (required), step, +3 more.
pdf_metadataC
Reads (or writes) metadata to a PDF. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), title, author, output, +2 more.
pdf_nupB
N-Up Page Imposition: Combine multiple pages per sheet in a 2, 4, 9, or 16-up grid layout. [Input: .pdf | Output: .pdf]
Inputs: input (required), output (required).
pdf_ocrB
Performs OCR on a PDF. [Input: Scanned PDF / Image | Output: Plain Text (.txt) / PDF]
Inputs: input (required), output (required).
pdf_overlay_underlayC
Overlay & Underlay Stationary: Apply letterheads, watermarked stationary, and templates as background or foreground. [Input: .pdf | Output: .pdf]
Inputs: input (required), output (required).
pdf_page_numbersC
Adds page numbers to a PDF. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), output (required), format, position.
pdf_posterizeB
Multi-Sheet Poster Tile Slicer: Tile oversized PDF pages across a grid of standard printable sheets with overlap margins and cut guides [Input: .pdf | Output: .pdf]
Inputs: input (required), output (required), scale, grid_cols, +4 more.
pdf_rag_chunksC
Extract semantic RAG chunks from PDF. [Input: PDF (.pdf) | Output: JSON array]
Inputs: input (required), output.
pdf_read_formA
Extract AcroForm fields and values from a PDF. [Input: PDF (.pdf) | Output: JSON file (.json) or object]
Inputs: input (required), output.
pdf_redactB
Permanently redacts sensitive text glyphs, patterns, regexes, or specified bounding areas with blackout boxes and optional overlay text. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), output (required), x, y, +7 more.
pdf_remove_blankC
Removes blank pages from a PDF. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), output (required), sensitivity.
pdf_remove_signaturesB
Remove Digital Signatures: Strip digital signature fields, cryptographic locks, and widget annotations. [Input: .pdf | Output: .pdf]
Inputs: input (required), output (required).
pdf_renderC
Renders a PDF. [Input: PDF (.pdf) | Output: PNG/JPEG/WEBP images]
Inputs: input (required), output (required), format.
pdf_reorder_pagesC
Reorders pages. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), order (required), output (required).
pdf_repairB
Repairs a corrupted or malformed PDF by rewriting its cross-reference table.
Inputs: input (required), output (required).
pdf_rotateB
Rotates pages in a PDF. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: angle (required), input (required), pages (required), output (required).
pdf_sanitizeC
Deeply sanitizes a PDF document by removing metadata, scripts, attachments, and thumbnails. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), output (required), remove_scripts, remove_metadata, +1 more.
pdf_scale_pagesC
Scale Page Dimensions: Scale page dimensions between standard formats or percentages. [Input: .pdf | Output: .pdf]
Inputs: input (required), output (required).
pdf_searchB
Searches for a text query inside a PDF. [Input: PDF (.pdf) | Output: JSON array]
Inputs: input (required), query (required).
pdf_signB
Digitally signs a PDF document (Currently a stub). [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), output (required).
pdf_splitC
Splits a PDF into multiple single-page PDFs. [Input: PDF (.pdf) | Output: Multiple .PDFs]
Inputs: input (required), output_dir (required).
pdf_split_by_outlineB
Split PDF by Outline: Split multi-chapter PDF documents based on their /Outlines bookmark hierarchy [Input: .pdf | Output: .zip]
Inputs: input (required), output (required).
pdf_split_scanned_bookB
Split Scanned Book Spine: Detect center binding gutter spine and split two-up page scans into single pages. [Input: .pdf | Output: .pdf]
Inputs: input (required), output (required).
pdf_stampC
Stamp Image & Logo: Place coordinate-exact images, logos, and badges onto PDF pages. [Input: .pdf | Output: .pdf]
Inputs: input (required), output (required).
pdf_stitch_canvasC
Stitch Continuous Canvas: Combine multiple pages vertically or horizontally into a continuous single-page canvas. [Input: .pdf | Output: .pdf]
Inputs: input (required), output (required), direction, margin_pt, +1 more.
pdf_timestampC
Cryptographic Timestamp TSA: Apply RFC 3161 cryptographically verified TSA timestamp tokens. [Input: .pdf | Output: .pdf]
Inputs: input (required), output (required).
pdf_to_docxB
Converts a PDF document to DOCX format by extracting its text.
Inputs: input (required), output (required).
pdf_to_epubC
PDF to EPUB 3.0: Convert fixed-layout PDF documents into reflowable EPUB 3.0 eBooks [Input: .PDF | Output: ..EPUB]
Inputs: input (required), output (required).
pdf_to_htmlC
Converts a PDF document into responsive, styled HTML5 web page.
Inputs: input (required), output (required).
pdf_to_jsonB
Converts a PDF document into structured JSON with text, page statistics, and metadata.
Inputs: input (required), output (required).
pdf_to_markdownC
Converts a PDF document into Markdown formatted text. [Input: PDF (.pdf) | Output: Markdown (.md)]
Inputs: input (required), output (required).
pdf_to_pdf_aC
Converts a PDF to PDF/A format. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: input (required), output (required).
pdf_to_pptxB
Converts a PDF document to PPTX format via best effort slide generation.
Inputs: input (required), output (required).
pdf_to_xlsxB
Converts a PDF document to XLSX format by using best effort table extraction.
Inputs: input (required), output (required).
pdf_validateC
Validates a PDF document. [Input: PDF (.pdf) | Output: Plain Text (.txt)]
Inputs: input (required).
pdf_validate_signaturesB
Validate Digital Signatures: Cryptographically verify digital signatures, certificate chains, and document integrity. [Input: .pdf | Output: .json]
Inputs: input (required), output (required), baseline.
pdf_watermarkC
Applies a text watermark to a PDF. [Input: PDF (.pdf) | Output: PDF (.pdf)]
Inputs: text (required), input (required), output (required), angle, +3 more.
recipe_runA
Execute a .ppflow recipe against a local PDF file immediately (one-shot, no daemon).
Inputs: input (required), recipe (required), output, name_template.
semantic_searchB
Semantic vector or keyword search across document index
Inputs: query (required), input, limit.
watcher_listB
List all currently active hot folder watchers with their status and statistics.
Inputs: no named parameters.
watcher_startA
Start a headless hot folder watcher daemon on a local directory. When a PDF is dropped into the watched directory it automatically runs the specified recipe.
Inputs: dir (required), recipe (required), output_dir, name_template, +1 more.
watcher_stopA
Stop a running hot folder watcher by its ID.
Inputs: watcher_id (required).
workspace_searchC
Searches for a text query inside a workspace directory or document.
Inputs: query (required), dir, input, formats.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
TDQS
Scored across 95 tools
Several tools are near-exact aliases or overlapping: pdf_convert_html/html_to_pdf, pdf_convert_markdown/md_to_pdf, pdf_images_to_pdf/img_to_pdf, and batch_fill/cli_fill_batch. Extraction and search also blur together across pdf_extract_text, pdf_to_markdown, pdf_to_json, pdf_chunk, pdf_rag_chunks, semantic_search, workspace_search, and pdf_search, making misselection likely.
Most names use snake_case and a pdf_ prefix, but the set mixes pdf_, office_, excel_, cli_, watcher_, execution_receipt_, and bare names like semantic_search. The action naming is also uneven, with noun-style names such as pdf_info and pdf_metadata alongside verb-style tools, and duplicate aliases break the pattern.
95 tools is far beyond a well-scoped surface, even for a broad PDF/document toolkit. The count is inflated by duplicate aliases and many niche operations, though the domain is large enough that the overall breadth is not entirely unjustified.
Coverage is very extensive across conversion, editing, forms, OCR, redaction, security, signatures, workflow automation, watchers, and receipts. There are minor gaps such as real digital signing being a stub and no explicit page-insertion tool, but most document lifecycle operations are covered.
Maintenance
Related MCP Connectors
Privacy-first PDF tools over MCP: merge, split, rotate, delete, compress, protect, inspect.
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
PDF and image tools for AI agents: compress, merge, split, OCR, sign. Runs locally, never uploads.
Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.
Related MCP Servers
- AlicenseBqualityDmaintenanceA universal MCP server for document processing, conversion, and automation. Handle PDF, DOCX, HTML, Markdown, and more through a unified API and toolset.1328 npm140MIT

opendocswork-mcpofficial
AlicenseNot gradedqualityCmaintenanceRust-native MCP server for Office document processing (Excel, Word, PowerPoint) enabling sub-millisecond, local-first document manipulation and export to PDF.164GPL 3.0- AlicenseAqualityBmaintenanceRust-powered PDF toolkit over MCP: create, read, and analyze PDFs; extract text and entities for RAG; convert to Markdown; split/merge/rotate/reorder pages; manage form fields and annotations; encrypt documents. Runs locally via uvx oxidize-mcp.121,015 PyPI6MIT
- AlicenseNot gradedqualityCmaintenanceA local MCP server that drives PDFium and pypdf to perform comprehensive PDF operations including inspection, assembly, page editing, watermarking, rendering, extraction, form filling, encryption, compression, attachments, bookmarks, and metadata management.MIT