Herramientas

From Microsoft: converts PDF, Word, Excel, PowerPoint, HTML and other files or URLs to Markdown so agents can read and search them. A single convert_to_markdown tool over STDIO or local HTTP.

Extracts text and tables from PDFs; merges, splits and rotates pages, adds watermarks, fills forms and OCRs scanned documents. The official Anthropic skill behind Claude's document features; source-available, not open source.

Generates natively editable PPTX from PDFs, Word files, web pages and other sources, with native shapes, data charts and master layouts. Can also fill your own template and add animations and narration to finished decks. Needs Python 3.10+ and its dependencies.

Adds a searchable, copyable text layer to scanned PDFs, with automatic deskew, rotation and size optimization, outputting PDF/A by default. Built on Tesseract, supports 100+ languages and runs fully locally.

Unofficial Python library and CLI for driving Google NotebookLM (now Gemini Notebook): bulk-import sources, ask cited questions, and generate and download podcasts, videos, slides, quizzes and flashcards. Ships an agent skill. Relies on undocumented APIs and needs a Google sign-in.

Converts text to speech with Microsoft Edge's online TTS service and can generate subtitle files at the same time. No API key needed, with voices for many languages. Not an official Microsoft project and depends on that online service staying available.

Scans files and directories for personal data such as names, emails and credit card numbers using Presidio Analyzer, with configurable entity types, confidence thresholds and ignore rules. Needs Python 3.10+ and a spaCy language model.

Lightweight OCR built on PaddleOCR models converted to ONNX, recognizing Chinese and English by default on CPU alone. The rapidocr CLI reads text from screenshots, photos and scanned page images. Needs Python; downloads models on first run, then works offline. Convert PDFs to images first.

Open-source offline machine translation built on OpenNMT, usable as a CLI, Python library or GUI. Download language packages as needed; when no direct model exists it pivots through an intermediate language. Suits text you would rather not upload to the cloud.

Language and toolset for double-entry bookkeeping in text files: bean-check validates the ledger, bean-format normalizes it, and Fava or beanquery handle reports and queries. Plain-text ledgers are easy for agents to generate and keep in version control.

English prose linter that turns usage guides such as Garner's and advice from great writers into rules, flagging clichés, redundancy, bad comparisons and usage errors line by line, with JSON output for agents. Runs locally with Python; English only.

Uses Obsidian's community Local REST API plugin so agents can list, read, search, append to and delete notes, and insert content at a heading, block reference or frontmatter field. Install that plugin and configure its API key first.

Converts PDFs to editable Word files, keeping paragraphs, tables, images and layout as closely as possible, and can extract tables alone, handy when a contract or exam only exists as PDF. Needs Python; digital PDFs only, OCR scans first. No longer actively maintained by Artifex.

Works with Gmail, Calendar, Drive, Docs, Sheets, Slides, Tasks, Chat and other Google Workspace services, with multi-user OAuth and read-only mode. You create your own Google OAuth client and run it in HTTP mode.

Searches Google Flights for flights and the cheapest travel dates, filtering by route, date, cabin, stops, airline and alliance, good for trip planning. Open-source Python, no API key needed; built on reverse-engineered Google endpoints, so changes at Google may break it.

Scans codebases and dependencies for open-source licenses, copyright notices and package manifests, detecting licenses by full-text matching, with output in JSON, SPDX, CycloneDX and more, for open-source compliance reviews.

Simon Willison's website screenshot CLI: batch screenshots from YAML, record demo videos, export PDF and HTML, run JavaScript in pages to extract data, and dump accessibility trees. Built on Playwright; install a browser on first use.

Command-line reference and bibliography manager: add papers by DOI with metadata fetched automatically, search by author, title or tag, and import or export BibTeX. Each entry is a readable YAML file that agents can read and write easily; a web UI is included. Needs Python.

Web search through DuckDuckGo plus fetching and parsing page content, with built-in rate limiting and LLM-friendly result formatting. No API key needed; runs with a single uvx command.

Crawls an entire site, counts words and keywords per page, and checks technical SEO such as titles, meta descriptions, image alt text, H1s and social tags. Outputs JSON by default or an HTML report for agents to act on. Needs Python; the optional AI content review needs an API key.

From the X (Twitter) developer platform: a FastMCP server that turns the X API into tools to post, search posts and users, and manage DMs and lists, with an allowlist for which tools load. Needs X developer app credentials and a locally started Python server.

From Free Law Project: finds bad redactions in PDFs, where a black box covers text that can still be selected and copied, and outputs the leaked text and positions per page as JSON. Useful for lawyers checking filings before release. Needs Python 3.10+; may miss cases, so review important files.

The Docling project's official MCP: converts PDF, Word, PowerPoint and more into structured documents with layout and table detection and OCR for scans, and lets agents build new documents paragraph by paragraph and export Markdown. Local mode needs Python and uv, or use your own Docling Serve.

Connects to Odoo ERP so agents can search, create, update and delete customers, products, invoices and other records in natural language, with aggregations and attachment reading. In production, install the companion MCP module in Odoo; for testing, YOLO mode connects directly.