ツール

Fly.io's official CLI (fly): sign in, create and deploy apps, and list apps and check their status, reading fly.toml in the current directory to identify the app. Needs a Fly.io account.

Lets agents read and write your local Obsidian vault directly: search notes, append to daily notes, tidy tags and properties, and summarize reading or research notes by topic. No need to open Obsidian or install plugins; access is limited to the vault and can be read-only. Needs Node.js 20+.

Econometrician Pedro Sant'Anna's academic Claude Code setup (fork the repo to use it): Beamer/Quarto lecture slides, paper review and mock refereeing, R/Python analysis and replication packages, with specialist subagents and quality gates. Needs Git and Python; slides need XeLaTeX and Quarto.

Lets agents drive WinDbg's CDB/KD to analyze crash dumps, debug user-mode processes remotely and debug kernels, and triage many dumps in a batch. Windows only; requires WinDbg or Debugging Tools for Windows.

Docker's official MCP gateway (the docker mcp CLI plugin): runs servers from the Docker MCP Catalog in isolated containers, manages secrets, OAuth and tool toggles centrally, and gives multiple clients one endpoint. Built into Docker Desktop 4.59+; Docker CE and other setups must build the plugin.

Reads and writes Obsidian vaults from the terminal: search, view, create, edit, move and delete notes, and manage frontmatter and daily notes, without Obsidian running. Good for agents maintaining a personal knowledge base. Formerly Obsidian CLI.

Microsoft's official Azure skill set: deployment prep and validation, deployment, production diagnostics, AKS, quota lookup, compliance audits, cloud migration and Foundry; the plugin version also connects the Azure MCP Server. Needs an Azure account and az login.

Microsoft's official Azure plugin: bundles 20+ skills such as azure-prepare, azure-deploy, azure-diagnostics and azure-cost, and connects the Azure MCP and Foundry MCP to query resources, estimate costs, deploy and troubleshoot. Needs an Azure subscription and az login.

Uses the Qdrant vector database as a semantic memory layer for agents: store information and retrieve it by meaning, connecting to a remote instance or a local path, with FastEmbed generating embeddings by default. Maintained by Qdrant.

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.

HashiCorp's official server: looks up provider, module and policy docs in the Terraform Registry to help write IaC; with an HCP Terraform token it can also manage workspaces, variables and runs. Runs in Docker by default.

Brings the Brave Search API to agents: web, news, image, video and local business and place search, plus LLM-ready page context and AI summaries. Maintained by Brave; needs an API key.

Self-hosted open-source platform for contract and legal document analysis: detects cited laws and builds a citation graph, and its MCP server lets agents search the corpus, read texts and annotations, and follow citations. Deploy your own instance with Docker; have a lawyer review results.

Connects LLMs to ROS and ROS 2 robots: publish and subscribe to topics, call services and actions, set parameters, and read sensor and robot state, without changing robot code. The robot side needs rosbridge running.

A plugin marketplace with dozens of plugins: an enhanced skill-creator, scrapers for Bilibili, Douban and Feishu docs, China A-share news and US stock fundamentals, WeCom notifications, deep research and fact-checking, with docs in English and Chinese.

Audio plugin suite: transcription with local Qwen3-ASR or Whisper (MLX on Apple Silicon), speaker diarization, transcript correction, structured meeting notes and StepFun TTS. StepFun ASR and TTS need an API key.

Manages a Microsoft 365 tenant with one m365 command: SharePoint, Teams, OneDrive, Outlook, Planner, Power Platform and more, with JSON output and JMESPath filtering. An open-source PnP community project, not officially supported by Microsoft; register an Entra app before signing in.

Two-stage paper skills: planning studies the style of your target preprint server (e.g. PhilArchive, arXiv), finds gaps in the literature and scores a seven-dimension mock review; writing drafts and checks each chapter from the outline. Suits philosophy and interdisciplinary work; needs Python 3.

Lets Claude Code watch videos: extracts frames with ffmpeg and transcribes timestamped audio from local files or YouTube links, to review footage, summarize lectures or find on-screen text. Needs Node.js 20+ and ffmpeg (yt-dlp for YouTube); transcribe with local Whisper or a Gemini/OpenAI key.

Turns a paper (arXiv link or PDF) into method diagrams, slides with a generated image per page (PPTX/PDF export) and an in-depth HTML explainer with formulas, for lab meetings and lectures. No API key; images use Codex's built-in generator or, in Claude Code, a separate image skill.

Builds conference talks, lab meeting decks, defenses, lectures and grant reports to academic norms: assertion-style titles, slides ordered by the argument, one cited chart per results slide, and a closing conclusions slide. Pair with Anthropic's pptx skill; on claude.ai, enable code execution.

Self-hosted engine that maps lab results, checkup reports and wearable data to standard metrics so agents can chart trends, citing the source file for every number. uvx mirobody mcp gives the coding tools; full records need Docker and an LLM API key. A doctor should review results.

Two companion skills: /tutor-setup turns PDFs, lecture notes or a codebase into an Obsidian study vault with concept notes and practice questions, and /tutor quizzes you with multiple-choice questions on weak spots and tracks mastery. For students reviewing or self-studying; best viewed in Obsidian.

Jupyter's official tool for notebook assignments: once teachers mark up questions and solutions, the CLI generates student versions, collects submissions, auto-grades and produces feedback. Suits programming and data courses. Needs Python and Jupyter; assignments must use nbgrader's markup.