AI agent tools for OCR
Short answer: Our top pick for OCR: unstract, with the highest AgentPick Score (77/100) among tools tagged "ocr". Runners-up: claude-real-video (69) and pullmd (60). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | unstract | LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows | 77/100 | ★ 7.3k | AGPL-3.0 | 14 Oct 2026 |
| #2 | claude-real-video | Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT. | 69/100 | ★ 2.2k | MIT | 8 Oct 2026 |
| #3 | pullmd | Self-hosted URL- and file-to-Markdown service for humans and AI agents - web pages, documents, images, audio, YouTube. PWA + REST + MCP + Claude Code … | 60/100 | ★ 487 | AGPL-3.0 | 14 Oct 2026 |
| #4 | RPA | Browser and desktop automation with an MCP server for AI assistants. Record macros or write JavaScript to automate websites, extract data, and control… | 59/100 | ★ 2.1k | See repo | 13 Oct 2026 |
| #5 | nuphus-mcp | Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio).… | 59/100 | ★ 325 | MIT | 13 Oct 2026 |
| #6 | typesafe-computer-use | Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS. | 54/100 | ★ 1.2k | MIT | 29 Sept 2026 |
| #7 | markdownify-mcp | A Model Context Protocol server for converting almost anything to Markdown | 49/100 | ★ 3k | MIT | 25 Sept 2026 |
| #8 | latex-document-skill | Universal LaTeX document skill for Claude Code: 27 templates, 27 scripts, 26 reference guides. Made with Claude Code on ✦ HappyCapy AI ✦ platform | 36/100 | ★ 786 | See repo | 13 Oct 2026 |
| #9 | imagesorcery-mcp | An MCP server providing tools for image processing operations | 30/100 | ★ 333 | MIT | 19 May 2026 |
| #10 | AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction | AI Bank Statement Document Automation By LLM model and Personal Finanical Analysis | 28/100 | ★ 626 | Apache-2.0 | 2 Aug 2026 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Grant the narrowest permissions the server allows.
- Check whether it runs locally or calls a remote service.
- Prefer servers listed in the official MCP registry.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for local-first setups →
MCP servers
AI agent tools for knowledge graphs and bases →
MCP servers
AI agent tools for RAG (retrieval-augmented generation) →
MCP servers
AI agent tools for MCP client →
MCP servers
AI agent tools for cybersecurity →
MCP servers
AI agent tools for DevOps →
MCP servers
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.