도구

Provides a sequential_thinking tool that guides the model to break complex problems into revisable, branching steps. Good for planning, analysis and tasks that need careful iteration. Official MCP reference server.

Astral's extremely fast Python package and project manager written in Rust, replacing pip, pipx, poetry, pyenv and more. Supports lockfiles and multiple Python versions, and uvx runs Python tools without installing them.

Open-source, LLM-friendly web crawler that turns pages into clean Markdown for RAG and agents. Ships the crwl CLI and supports deep crawling and question-driven data extraction (extraction needs an LLM key). Free to self-host.

Document parser from OpenDataLab that turns PDFs, images and Office files into Markdown or JSON, handling tables, formulas and complex layouts well, with page-by-page reading and citation anchors for agents. Parses locally by default; needs Python 3.10+.

Write videos in HTML, CSS and frame-seekable animations, preview them from the CLI and render deterministic MP4s. Comes with agent skills for product launch videos, captions and talking-head re-edits. Maintained by HeyGen; needs Node.js 22+ and FFmpeg.

HeyGen's official HyperFrames skill set: lets agents write deterministic MP4 videos in HTML, CSS and animation, with workflows for promo videos, explainers, captions and beat-synced music. Needs Node.js 22+ and FFmpeg.

Job search system that runs in your local AI coding CLI: scans job portals, scores roles with a structured A-H evaluation and a 1-5 rating, flags fake listings, tailors ATS resumes and cover letters, and tracks applications. Never submits for you. Needs Node.js.

Multi-agent orchestration framework for Claude Code and Codex, formerly Claude Flow: swarm coordination, self-learning memory and cross-machine federated communication. The marketplace offers 30+ plugins; full features need npx ruflo init.

Multi-agent orchestration framework formerly called Claude Flow: ruflo init gives Claude Code nearly 100 specialized subagents, swarm coordination, cross-session vector memory and hooks; add --codex to configure Codex instead. Also works as a standalone MCP server or plugin marketplace.

Classic open-source OCR engine and CLI that reads text from images and outputs plain text, hOCR, searchable PDF or TSV. Supports 100+ languages; install the language data for each language you need.

All-in-one LLM fine-tuning framework: llamafactory-cli handles pretraining, SFT, PPO/DPO alignment and LoRA/QLoRA training, plus chat inference, weight merging and export, and OpenAI-style API serving for 100+ open models. Has a Web UI; training usually needs a GPU.

Command-line edition of the open-source OpenBB investment research platform: query stock prices, financial statements, macroeconomic and other financial data from the terminal, and automate data pulls with Routine scripts. Officially maintained; some sources need API keys.

Official OpenBB MCP server exposing the OpenBB Platform's equity, ETF, macroeconomic, crypto and news data to agents; enable only the tool categories you need to save context. Needs uv locally; some data sources need your own API keys. Not investment advice.

Parses PDF, DOCX, PPTX, XLSX, HTML, images and audio, recovering layout, reading order, tables and formulas, and exports Markdown, HTML or lossless JSON. Started by IBM Research, now hosted by the LF AI & Data Foundation; runs fully locally.

Command-line toolkit for transcoding, cutting, joining, frame extraction and streaming of audio and video, including ffmpeg, ffprobe and ffplay. A core dependency for agents handling media. The GitHub repo is the official mirror.

Generates self-contained HTML+SVG diagrams in an editorial style: architecture, flowcharts, sequence, swimlane, Gantt and dozens more types. Can match brand colors from a website and redraw imported Mermaid, draw.io and Excalidraw sources.

Multi-agent simulated hedge fund: agents modeled on investors like Buffett and Munger work with quant and risk modules to analyze stocks, with backtesting. Good for teaching investment frameworks. Needs Financial Datasets and model API keys; no real trading, not investment advice.

Official MCP for the open-source design tool Penpot: through the Penpot plugin API, agents can query, modify and generate designs, supporting design-to-code and code-to-design. Run npx -y @penpot/mcp@latest first and load the MCP plugin in Penpot to connect.

'rsync for cloud storage': sync and copy files across dozens of providers such as S3, Google Drive, OneDrive and Alibaba Cloud OSS, with encryption and mounting. Set up remotes with rclone config before use.

Conversion rate optimization skill from the marketingskills collection: give it a homepage, landing page, pricing page or form and it diagnoses value proposition, headlines, CTAs, trust signals and friction, returning quick wins, high-impact changes, A/B test ideas and alternative copy.

QGIS command-line wrapper from HKU's CLI-Anything project: create and edit .qgz projects, add GeoPackage layers and features, build print layouts and export PDF or images, and call QGIS processing algorithms, with JSON results. Needs QGIS desktop and a Python that can import PyQGIS.

From HKU's Data Intelligence Lab: plugins or skills for Claude Code, Codex and other agents generate agent-callable CLIs for apps like GIMP, Blender and LibreOffice, and the cli-hub package manager finds and installs ready-made community CLIs. Needs Python 3.10+.

Personalized tutoring system from HKU's HKUDS: build a knowledge base from textbooks for Q&A, step-by-step solutions and quizzes, for teachers and self-learners. The deeptutor command outputs JSON for agents like Claude Code. Needs Python 3.11+, Node.js 20+ and an LLM API key.

Modern markup-based typesetting system, a LaTeX alternative for papers, reports and resumes. Fast incremental compilation; typst compile outputs a PDF in one command and watch mode recompiles automatically.