Tools

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.

Crowdin's official CLI: push source files and pull translations back in place, track progress, manage glossaries and TM, and run machine or AI pre-translation, with JSON output for agents. Needs a Crowdin account (free trial; free for open source) and a token; crowdin init sets up config.

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.

Lets agents create, update and resolve incidents in ServiceNow, manage the service catalog, change requests and knowledge articles, and load only the tools each role needs. Needs a ServiceNow account and Python 3.11+ (from source); community-maintained, last updated Oct 2025.

The Dart team's official MCP server (dart mcp-server): analyze project errors, search pub.dev and manage dependencies, connect to running Flutter apps for hot reload, and read runtime errors and the widget tree. Needs Dart 3.9+; still experimental.

Alibaba Cloud's official agent skills: ECS diagnosis and DR, RDS/PolarDB database checks, PAI training and EAS deployment, ACK clusters, RAM permissions, OSS and network troubleshooting, and Model Studio. Needs an AccessKey or aliyun CLI credentials.

Firecrawl's official plugin: brings the Firecrawl CLI in as skills so Claude Code can search the web, scrape pages to Markdown, map site links or crawl whole sites. Install firecrawl-cli and set an API key first; self-hosting supported.

Renders a screen reader spec for a component directly in Figma: focus order plus per-state VoiceOver (iOS), TalkBack (Android) and ARIA (Web) property tables and announcements. Part of uSpec; reads the component .md spec from create-component-md and needs a Figma MCP and a configured template key.

i18next's official CLI: finds hard-coded strings in JS/TS code, extracts translation keys, checks which locales are missing entries and syncs locale files; init --yes sets up non-interactively, and a bundled agent skill guides app internationalization. Needs a Node.js project using i18next.

Nulab's official Backlog MCP: lets agents manage Backlog projects, issues and comments, milestones and wikis, and view Git repositories and pull requests. Needs your Backlog space URL and a personal API key, plus Node.js or Docker.

MinerU's official MCP: parses PDF, Word, PowerPoint and images into Markdown via the mineru.net cloud API, keeping tables and formulas. The keyless Flash mode works out of the box; add a token for higher quotas and more formats.

Comet's official Opik MCP: query traces and spans of LLM apps in chat, log scores and comments, and manage datasets, experiments and prompt versions. Works with Opik Cloud (API key or browser sign-in) and self-hosted open-source Opik.

Diagnoses page-load and interaction performance from Chrome DevTools traces, network evidence and source code, covering Core Web Vitals, LCP and layout shifts. Separates measured values from estimates and hypotheses, and re-measures fixes under equivalent conditions.

Implements, debugs or audits how a website behaves on iPhone and iPad in Safari or added to the Home Screen, and on Mac when added to the Dock: safe areas, status and address bar tinting, theme color, overlays, keyboard, manifest, icons, splash screens and installed navigation.

Lets agents run the CodeRabbit CLI to review local changes, listing bugs and security issues by severity, and fix unresolved CodeRabbit comments on a PR after you confirm each one. Maintained by CodeRabbit; needs the CLI installed and signed in. Free tier available.

MongoDB's official plugin: runs the MongoDB MCP locally via npx and adds skills for query generation, index tuning, schema design, and full-text and vector search. Connects to self-hosted or Atlas databases with a connection string.

MongoDB's official skill library covering document model design, driver connection setup, query optimization, natural-language query generation, Atlas full-text and vector search, and stream processing. Works alongside the MongoDB MCP Server.

HeyGen's official CLI, built for agents like Claude Code and Codex: generate avatar presenter videos from a prompt or template, translate and dub videos, and synthesize speech, with JSON output. Good for batch training and product videos. Needs a HeyGen API key (usage-billed) or a Pro/Max plan.

Miro's official plugin with the Miro remote MCP and three skills: draw codebase explanations on a board, run visual code reviews on the board, and turn board docs, diagrams and prototypes into development specs. Needs OAuth with a Miro account.

Official skills from US broker Alpaca: teach agents to backtest, place and check paper trades, plus developer guides for Broker API account opening, funding and reconciliation. Needs an Alpaca API key (paper trading uses no real money) and the Alpaca CLI; results need professional review.

Slack's official plugin: connects the Slack-hosted MCP to search messages and files, send or schedule messages, and read and write canvases. Includes commands for channel summaries and standup reports, plus skills for building Slack apps. Requires workspace admin approval.

Community-run local Salesforce MCP: query, summarize and update accounts, opportunities and cases in plain language and search across objects; admins can also create custom objects and fields and edit Apex. Needs Salesforce login and security token (or a Connected App) and Node.js 22+.

Microsoft Translator's translation quality tool: GPT scores each sentence using MQM error categories or a direct score; --list_mqm_errors shows error types and severity. Needs line-aligned source and target files, Python and an OpenAI or Azure OpenAI key (paid); a translator should still review.