AI agent tools for document processing
In this catalog, a document processing tool is one that reads, converts, fills or generates PDFs, Word files and other documents. Our enrichment pass tags 179 listings with it: 68 MCP servers, 48 agent skills, 9 plugins, 2 agent frameworks, 51 AI agents and 1 no-code agent builder. By listing rank, the top MCP server is anymd, the top agent skill is career-ops and the top AI agent is Gemini CLI. 13 of the 179 are published by the vendor behind the product, and 118 were active in the last 30 days. 4 of the 68 MCP servers run only as remote servers, with nothing to install locally. Each entry below links to its listing page, with grades, install commands and sources.
Updated Oct 26, 2026 · Built from catalog data; how we rank and grade
What the job is
- Tagged listings
- 179
- By type
- 68 MCP servers, 48 agent skills, 9 plugins, 2 agent frameworks, 51 AI agents and 1 no-code agent builder
- Published by the vendor
- 13 of 179
- Active in the last 30 days
- 118 of 179
- Open source
- 119 of 179
- MCP servers that run only remotely
- 4 of 68
- Hosts named by the MCP servers
- Claude Code (66), Cursor (66), VS Code (66)
Building blocks by type
The top entries of each type, by listing rank. Open a listing for its install command, grades and sources.
MCP servers 68 tagged
- 1anymd
SylphxAI
Any file → clean Markdown for AI agents: PDF, Office, EPUB, HTML, images, audio/video.
- 1.1K GitHub stars
- Active in the last 30 days
- Open source (MIT)
★ 1.1KLast active Oct 21, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2
AFreshness: A–Security: not graded yet - 2Word MCP Live
ykarapazar
Live Microsoft Word editing via MCP — tracked changes, undo, comments, 40+ tools
- Active in the last 30 days
- Open source (MIT)
★ 239↓ 673/wkLast active Oct 6, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2
AFreshness: A–Security: not graded yet - 3Firecrawl MCP Server
firecrawlOfficial
Firecrawl, the context API for AI agents: search, scrape, interact with the web, plus paper search.
- Published by the vendor
- Most GitHub stars here (7,676)
- Runs locally or as a remote server
★ 7.7KLast active Oct 23, 2026Local (stdio), Remote (HTTP)Claude Code, VS Code, Codex, Cursor +2
AFreshness: A–Security: not graded yet - 4PDF MCP
jztan
Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.
- Most weekly downloads here (770)
- Active in the last 30 days
- Open source (MIT)
★ 155↓ 770/wkLast active Oct 8, 2026Local (stdio)Claude Code, Codex, VS Code, Claude Desktop +2
AFreshness: A–Security: not graded yet - 5kordoc
chrisryugj
Parse Korean documents (HWP, HWPX, PDF, XLSX, DOCX, PPTX) to Markdown; fill forms, diff, render.
- 2.7K GitHub stars
- Active in the last 30 days
- Open source (MIT)
★ 2.7KLast active Oct 26, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2
AFreshness: A–Security: not graded yet
Agent skills 48 tagged
- 1career-ops
career-ops-hq
Open-source AI job search agent -- evaluate offers, generate CVs, scan portals, track applications.
- Largest repository here (76,979 stars)
- Active in the last 30 days
- Open source (MIT)
★ 77KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 2gcode
earthtojake
Slice 3D models into printer-ready G-code with OrcaSlicer, the open-source slicer with built-in profiles for most FDM printers (Prusa, Bambu Lab, Creality…
- Repository has 22.9K stars
- Active in the last 30 days
- Open source (MIT)
★ 22.9KLast active Oct 20, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 3gpu-document-processing
langchain-aiOfficial
Use when processing large PDFs, document collections, or bulk text extraction tasks that benefit from GPU-accelerated processing.
- Published by the vendor
- Repository has 30.6K stars
- Active in the last 30 days
★ 30.6KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 4attach-image
PrimeIntellect-ai
Load an on-disk image (PNG, JPEG, GIF, WebP) into the model's context as a viewable attachment so the model can directly SEE it — for screenshots, diagrams…
- Repository has 22.3K stars
- Active in the last 30 days
- Ships helper scripts
★ 22.3KLast active Oct 21, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 5pdf-explore
Companion-Inc
Read, extract, and cross-check content across scientific PDFs.
- Repository has 10K stars
- Active in the last 30 days
- Open source (MIT)
★ 10KLast active Oct 24, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet
Plugins 9 tagged
- 1
KiCad Studio Kitoaslananka
The complete KiCad development environment for VS Code — view schematics & PCBs, run DRC/ERC, export production files, search components, and get AI-powered…
- Active in the last 30 days
★ 19Last active Oct 22, 2026VS Code, Cursor, Windsurf, VSCodium
AFreshness: A–Security: not graded yet - 2
Folio DOCXstll
Open .docx files in VS Code and edit them on laid-out pages: type, track changes, comment, and save back to the same file.
- Most GitHub stars here (31)
- Active in the last 30 days
- Open source (Apache-2.0)
★ 31Last active Oct 24, 2026VS Code, Cursor, Windsurf, VSCodium
AFreshness: A–Security: not graded yet - 3
AI Markdown to PDFjcendal
Convert AI-generated Markdown files to polished PDFs with Mermaid diagrams rendered as real SVG graphics.
- Open source (MIT)
★ 2Last active Aug 5, 2026VS Code, Cursor, Windsurf, VSCodium
BFreshness: B–Security: not graded yet - 4
Markdown Reader with CopilotJinqiShen
Review Markdown, Word (.docx), and PowerPoint (.pptx) with inline commenting, AI agent tools, and Copilot integration
- Open source (MIT)
★ 3Last active Aug 25, 2026VS Code, Cursor, Windsurf, VSCodium
BFreshness: B–Security: not graded yet
Agent frameworks 2 tagged
- 1docx-editor
superdoc
Browser DOCX editor and document engine built on OOXML, with a Document API that agents reach through SDKs, a CLI and an MCP server.
- 1.1K GitHub stars
- Active in the last 30 days
- Open source (AGPL-3.0)
★ 1.1KLast active Oct 24, 2026
AFreshness: A–Security: not graded yet - 2PageIndex
VectifyAI
Python library that builds a tree index of long documents and has an LLM reason through it to retrieve answers, without a vector database or chunking.
- Most GitHub stars here (39,601)
- Most weekly downloads here (43.6K)
- Active in the last 30 days
★ 39.6K↓ 43.6K/wkLast active Oct 24, 2026
AFreshness: A–Security: not graded yet
Search agent frameworks for document processing → All harnesses & sdks
AI agents 51 tagged
- 1Gemini CLI
Google
Open-source terminal agent that queries and edits codebases and automates tasks with Gemini models
- Most GitHub stars here (107,694)
- Most weekly downloads here (231.3K)
- Active in the last 30 days
★ 107.7K↓ 231.3K/wkLast active Oct 23, 2026
AFreshness: A–Security: not graded yet - 2pinvou-agent
Pinvou
Open-source desktop agent workspace for document work, visual design and coding over ACP.
- 2.6K GitHub stars
- Active in the last 30 days
- Open source (MIT)
★ 2.6KLast active Oct 24, 2026
AFreshness: A–Security: not graded yet - 3feynman
Companion-Inc
Open-source CLI research agent for literature reviews, deep research and paper drafts.
- 10K GitHub stars
- Active in the last 30 days
- Open source (MIT)
★ 10KLast active Oct 24, 2026
AFreshness: A–Security: not graded yet - 4LobsterAI
netease-youdao
Open-source desktop agent that edits files and Office documents and takes tasks from chat apps.
- 6.1K GitHub stars
- Active in the last 30 days
- Open source (MIT)
★ 6.1KLast active Oct 23, 2026
AFreshness: A–Security: not graded yet - 5open-cowork
OpenCoworkAI
Free open-source desktop app for Windows and macOS that runs AI agents with one-click install, sandboxed workspaces and Skills.
- 2.2K GitHub stars
- Active in the last 30 days
- Open source (MIT)
★ 2.2KLast active Oct 20, 2026
AFreshness: A–Security: not graded yet
No-code builders 1 tagged
- 1Microsoft Power Automate
Microsoft
Microsoft's low-code automation service for cloud flows, desktop robotic process automation and process mining, with Copilot to build flows in plain language
CFreshness: C–Security: not graded yet
Search no-code builders for document processing → All no-code builders
For business buyers: agents with stated pricing
Only agents whose listing states pricing are shown, with what the listing says. Check the publisher's pricing page before you buy.
| Agent | Pricing in its listing | Source |
|---|---|---|
| ElicitElicit | Freemium with a free tier; $0 to $89 per month; pricing page checked Oct 2026 | Pricing page |
Questions
- What are the top tools for document processing?
- By listing rank, the top MCP server is anymd, the top agent skill is career-ops and the top AI agent is Gemini CLI. Rank weighs adoption, freshness, documentation and publisher identity; money never changes it.
- How many tools does the catalog list for document processing?
- 179 listings are tagged for it: 68 MCP servers, 48 agent skills, 9 plugins, 2 agent frameworks, 51 AI agents and 1 no-code agent builder. Tags come from an automated enrichment pass over the top-ranked listings, so tools outside that pass are not counted.
- Which AI apps do the MCP servers work with?
- Of the 68 MCP servers, 66 list Claude Code, 66 list Cursor and 66 list VS Code as a supported host. Open a listing for its install command and the other hosts it names.
- Do the AI agents for document processing cost money?
- Pricing is stated for 1 of the 51 agents: Elicit (freemium with a free tier). The other agents state no pricing in their listings.
179 listings are tagged for this use case; the lists above show the top entries.
Related
- IndustryAI agent tools in research and academia
- IndustryAI agent tools in legal
- IndustryAI agent tools in construction and architecture
- Use caseAI agent tools for spreadsheets
- Use caseAI agent tools for writing and editing
- Use caseAI agent tools for data analysis
- Host guideAdd-ons for Claude Code
- Host guideAdd-ons for Cursor