도구

Browser automation MCP built on Selenium WebDriver for Chrome, Firefox, Edge and Safari: locate elements, click and type, upload files, take screenshots, run scripts, and handle alerts and cookies. A good fit for test teams already using Selenium.

Official FinLab quant skill: lets agents use FinLab data (mainly Taiwan stocks, plus US, Japan, Korea and Hong Kong) to write stock-picking strategies, run backtests and analyze factors. Needs a FinLab account (free tier has a daily data cap), Python 3.10+ and uv. Not investment advice.

Lets agents run local ComfyUI workflows to generate images, audio and video, regenerate from earlier results with new parameters, check the queue and switch models. Install and start ComfyUI, then clone this repo and run the server with Python (port 9000 by default).

Connects to self-hosted or managed Nextcloud so agents can manage files, calendars, contacts, notes, Deck boards and mail, and read PDF and Word content (OCR for scans is opt-in); suits teams that value data ownership. Needs a Nextcloud account with an app password, and uv.

One learn-faster command turns Claude Code into a learning coach: builds a syllabus for your level, schedules spaced review, sets exercises and tracks progress, with an exam-prep mode. Needs uv and Claude Code; Codex: run learn-faster init --agent codex (lighter onboarding).

Official Databricks plugin with skills for the CLI and auth, Genie data queries, Apps, Lakebase, Lakeflow jobs and pipelines, Model Serving and DABs deployment, plus hooks for prompt routing, session context and auth failure hints. Needs a Databricks account.

Official Databricks skills guiding agents to build Lakeflow pipelines and jobs, Apps, Lakebase, Vector Search, Model Serving and AI/BI dashboards on the lakehouse. Needs the Databricks CLI.

Official testing skills from TestMu AI (formerly LambdaTest) covering 40+ frameworks including Selenium, Playwright, Cypress, Appium, pytest and JUnit, guiding agents to write unit, end-to-end and mobile tests. Runs locally; cloud cross-browser and real-device runs need an account.

Describe the video you want and the agent builds a reproducible edit project: footage, storyboard, bilingual subtitles, transitions, intro and outro, rendering and QA. Needs Node.js and ffmpeg; AI voice and assets need ListenHub. Science mode uses the author's voice and outro by default.

Manage Anki cards from the command line: add notes in bulk from Markdown and list or review cards by query, without Anki running. Needs an existing local Anki database and profile; not an official Anki project.

Apache Doris's official MCP: gives agents read-only access to explore table metadata, run and explain SQL, diagnose slow queries, and check cluster status, load jobs and data governance info. Needs Python 3.12+ and Doris 2.0 or later.

Socratic teaching skill: when your message includes Socrates or socratic, the agent reads the code, docs or PDF you provide and guides you to the answer through layered questions instead of giving it away. Good for tutoring and self-study; prompt-only, nothing else needed.

Leads a visible, verified code walkthrough in Neovim: confirms real behavior by running code, then authors one immutable Navi tour with short notes the viewer steps through, optionally recorded with OBS. Requires Terminal Control (termctrl), Neovim 0.10+ and navi.nvim.

Railway's official plugin, bundling the use-railway skill and hosted Railway MCP so agents can create projects, deploy services, set environment variables and databases, and check logs and metrics to debug deployments. Needs a Railway account.

IELTS prep coach with four skills: a level check with practice advice, essay marking and rewrites on the four criteria, reading mistakes and paraphrase breakdowns, and Speaking Part 2 stories with Part 3 prep. Prompt-only, no API key; no saved history, and scores are AI estimates.

ComfyUI's official MCP: lets agents drive local ComfyUI image and video workflows, list installed nodes, models and templates, submit jobs and fetch results, and start or stop ComfyUI. Needs a machine that can run ComfyUI (usually a GPU) and comfy-cli; partner models consume Comfy credits.

Local image processing MCP: crop, resize, rotate, add text and watermarks, blur, remove backgrounds, detect objects and extract text with OCR, with no images uploaded anywhere; handy for photos, scans and course visuals. Needs Python 3.10 and pipx; first install downloads detection models.

QuantConnect's official CLI drives the open-source LEAN engine locally or in the cloud to download data, backtest and optimize quant strategies and deploy them live. Requires a paid-tier QuantConnect organization; strategies in Python or C#; local runs need Docker. Get expert review.

Vercel's official plugin: a knowledge graph of the Vercel ecosystem, dozens of skills, expert subagents for deployment and performance, and commands for deploys, env vars and project status, covering Next.js, the AI SDK, storage and CI/CD. Needs Node.js 18+ and Bun; telemetry is opt-out.

Official Readwise skills: triage your Reader queue, skim feeds, quiz you on what you just read, and draft book reviews and reading recaps from your highlights. Needs a Readwise subscription (30-day free trial) and the Readwise MCP or CLI installed first.

Postman's official MCP server: lets agents manage workspaces, collections, environments and API specs, help with API testing and generate client code from API definitions. The remote version uses OAuth; the local version needs a Postman API key.

MCP for the Canvas LMS: teachers can have agents bulk-grade, manage assignments and modules, post announcements and nudge students with missing work; students can check deadlines and grades. Needs a Canvas API token; one-click extension for Claude Desktop, Python 3.11+ elsewhere.

Cross-platform UI automation skills built on Midscene.js visual recognition: control browsers, desktops, Android, iOS and HarmonyOS devices in natural language, and set up Vitest + Midscene E2E tests. Bring your own vision model API key; maintained by the Midscene team.

Hugging Face's official MCP server: lets agents search models, datasets and Spaces on the Hub and call thousands of Gradio AI apps directly. Hosted remotely; sign in with your Hugging Face account or authorize with a token.