도구

Gives agents 250+ Financial Modeling Prep endpoints: financials, valuation and technical indicators, insider and congressional trades, SEC filings and earnings calendars. Needs an FMP API key (free tier); connect to the author's hosted URL or run locally on Node.js 25.3+. Results need expert review.

Styles elevated surfaces such as cards, dialogs, popovers and toasts with smooth-shadow-ring utilities instead of pairing a border or ring with a shadow, avoiding the double-edge look. Covers ring and shadow tinting, dark mode and overrides. Requires the shadow-plugin Tailwind plugin.

Webflow's official MCP: manage your site's pages, CMS content and blog posts by chat, and with the MCP Bridge App in the Designer, edit page elements and styles directly. Needs a Webflow account and Node.js 22.3+; first connection asks you to authorize sites.

Microsoft's official MCP: query Clarity traffic, behavior metrics and session recordings in plain language, filtered by device, browser, country and more, to dig into landing page conversion. Needs Clarity installed on your site, a data export API token and Node.js.

Connects any FHIR-compliant EHR server (e.g. the Epic sandbox or HAPI) to agents to search, read, create and update patient clinical data in plain language, with SMART on FHIR auth. By WSO2. Needs a FHIR server URL, access token and uv; clinicians must review results.

Connects to the St. Louis Fed's FRED database: search and pull 800,000+ macroeconomic time series (GDP, unemployment, inflation, interest rates) with built-in year-over-year and period-over-period changes. For macro research, investing and teaching. Needs a free FRED API key and Node.js.

Lokalise's official CLI (lokalise2) covering the Lokalise API v2: upload and download language files and manage keys, translations, screenshots, translation tasks and contributors. Needs a Lokalise account (paid, 14-day free trial) and an API token passed via --token.

Runs locally with no API key: looks up drug labels and adverse events from FDA, EMA and DailyMed, plus WHO health statistics, PubMed papers, clinical trials and clinical guidelines, with auto-generated evidence-level tags on papers. Needs Node.js. Have a doctor or pharmacist verify results.

Diffs a live page's accessibility violations against a baseline, stashing uncommitted changes by default or comparing with a branch, and reports new, fixed and pre-existing WCAG issues with selectors and fixes. Locates only, no edits. Runs AccessLint's Chrome and CLI tools via npx.

Runs the AccessLint rule engine against a live page and returns a worklist of WCAG 2.2 violations, each with its DOM selector, source file and line when mapped, evidence and a suggested fix. Locates without editing; sets up a debuggable Chrome and runs the CLI via npx.

Guides building small always-on WebGL visuals (avatars, ambient orbs, glass and iridescent surfaces) inside product UI: one shared context, a single capped frame loop, cheap fragment shaders, context-loss handling, a mandatory non-WebGL fallback, and React SSR and Server Components pitfalls.

Makes the agent use Tailwind container queries instead of viewport breakpoints for responsive components, migrating sm:/md:/lg: classes to @container variants. Explains when page-level layout should keep viewport breakpoints and lists common review mistakes. Tailwind v3 needs a plugin.

Sonar's official plugin bringing SonarQube checks into the agent coding loop: secrets-scanning hook, issue fixing, quality gates, coverage and dependency risk; with Vortex analysis on, every edit is checked. Needs SonarQube (free Community Build works), the sonar CLI and Docker.

From Twilio Labs: exposes Twilio's public APIs (SMS, voice, phone numbers, Serverless and more) as MCP tools generated from its OpenAPI specs, with filtering by service or tag. Needs a Twilio API key; marked as a proof of concept.

Shapes the agent's own replies rather than your documents: separates what changed from what was verified, cuts invented confidence, leads with the action and keeps load-bearing caveats. Manually invoked and stays on until you say stop; a script can enable it in CLAUDE.md or AGENTS.md.

Neon's official plugin combining the Neon MCP and skills to manage serverless Postgres: projects and branches, object storage, Functions and the AI Gateway. Signs in to Neon via OAuth the first time you use the MCP.

Connects to PACS and other DICOM servers: query images by patient, study and series, read text from PDF reports embedded in DICOM, and forward series to AI nodes such as segmentation. Needs uv and a YAML config. Not for clinical use or real patient data (per the author).

Official Google Ads API assistant: ask in plain language, generate and validate GAQL queries, run them to export account data to CSV, and debug offline conversion uploads. Account-changing code is generated, not run. Needs a developer token, credentials file and Python 3.10+.

Analyzes your codebase and generates a render.yaml Blueprint, or creates services directly through the Render MCP, to deploy apps to Render. Maintained by Render and included in OpenAI's curated skills. Needs a Render account and code pushed to GitHub, GitLab or Bitbucket.

Wolfram's official agent tools: use the Wolfram Language and Wolfram|Alpha for symbolic and numeric math and scientific and statistical data, for teaching and research. The command runs the official Docker image with a free developer license; Wolfram 15+ users can install it in the app.

Searches 600,000+ studies registered on ClinicalTrials.gov, shows protocols and posted results (efficacy, adverse events), and matches patients to recruiting trials by age, sex, condition and location. Public data, no API key; needs Node.js 24+. Unofficial; results must be reviewed by a doctor.

PostHog's official plugin with a built-in MCP and 30+ skills: query product analytics, feature flags, A/B experiments, dashboards and error tracking from chat, and optionally send Claude Code sessions to LLM Analytics. Needs OAuth sign-in with a PostHog account.

MLflow's official skills plugin: lets coding agents add MLflow Tracing to LLM apps, analyze failed traces, build evaluation datasets and scorers, and query token and latency metrics, closing the instrument, evaluate, iterate loop. Needs MLflow 3.8+.

Fixes janky web animation by moving width, height, position and box-shadow animations onto compositor-only transform and opacity, using pseudo-element opacity for shadows and the FLIP technique for layout changes and height: auto, to reach smooth 60/120fps motion.