ツール

Sentry's official remote MCP: lets coding agents query errors, issues, stack traces and performance traces, and call Seer for root-cause analysis. Sign in with OAuth, or connect to self-hosted Sentry over stdio.

Lets agents manage Google Cloud resources in natural language through the gcloud CLI, blocking interactive and other agent-unfriendly commands by default, with configurable allow and deny lists. A preview release from Google, not an officially supported product; install gcloud and sign in first.

Translates articles between Chinese and English or Chinese and Japanese (not English-Japanese) in four steps: analysis, draft, review and final, with options for target audience, style and glossary, aiming for natural-sounding output. No account or API key; URLs are fetched via r.jina.ai.

Plotting skills for academic papers: bar, line, scatter, radar and other styles distilled from 9 real paper figures. Plot your own data in a chosen style as 300 dpi figures, or reproduce a matplotlib script from a paper screenshot. Needs local Python and matplotlib.

AWS Labs' official plugin marketplace: deploy-on-aws (architecture recommendations, cost estimates and IaC deployment), aws-serverless, aws-amplify, databases-on-aws, sagemaker-ai and more. AWS suggests Agent Toolkit for AWS for new projects.

Lets coding agents read your codebase, extract a design system, then generate UI mockups, slide decks, posters and other marketing visuals on Superdesign's infinite canvas and iterate in branches. Needs @superdesign/cli and a Superdesign account; free to start.

Open-source plugin for agencies and brand teams: 163 skills and 24 specialist agents follow a 12-stage strategy flow to produce positioning, growth plans, multichannel campaigns, content, ad copy and reports, with claims and compliance checks before publishing. Multi-brand; uses many tokens.

HashiCorp's official plugin marketplace: the terraform plugin has 16 skills (configuration, modules, provider development, testing, import, Stacks and policy), and the packer plugin has 4 image-build and HCP Packer skills.

HashiCorp's official Terraform and Packer skills: write HCL in the official style, refactor modules, terraform test, provider development, Stacks and policy, plus AWS and Azure image builds.

Runs SQL queries against ClickHouse and browses databases and table schemas, read-only by default; can also enable embedded chDB to query data directly in files and URLs. Maintained by ClickHouse.

Jina AI's official remote MCP: converts web pages and PDFs to Markdown, searches the web, arXiv, SSRN and images, and offers screenshots, reranking and semantic dedup. Reading tools work without a key (rate-limited); search and rerank need a Jina API key.

Lays out a finished Markdown long-form post in the X (Twitter) Articles editor: title, bold, links, cover and inline images, with tables and Mermaid diagrams turned into images. Saves a draft only, never publishes. Needs X Premium Plus, Playwright MCP and Python (macOS/Windows).

From the X (Twitter) developer platform: a FastMCP server that turns the X API into tools to post, search posts and users, and manage DMs and lists, with an allowlist for which tools load. Needs X developer app credentials and a locally started Python server.

Drives desktop Excel on Windows: refresh Power Query, build pivot tables and charts, evaluate DAX and run VBA while keeping existing formulas and formatting, so finance and admin staff can automate existing reports. Needs Windows, Excel 2016+ and Node.js; no macOS.

From Vercel: discovers locally running Next.js 16+ dev servers and hands the runtime errors, routes and logs from their built-in MCP endpoint to the agent, and points the agent to docs matching your installed version.

Unofficial Yahoo Finance data tool with a yahoo-finance CLI, an MCP server and an agent skill: stock quotes, price history, financials, option chains and analyst ratings. Needs Node.js 22+, no API key. The API is unofficial and may change; for research only.

Describe what you need and get a typeset PDF: turn handwritten notes or scanned textbooks into LaTeX handouts and cheat sheets, make exams with answer keys, write papers, theses, posters, resumes and letters. 27 templates plus chart and mail-merge scripts. Needs TeX Live (install script included).

Microsoft's official skill: has the agent use Microsoft Learn docs to call Azure text and document translation, enforce glossaries, train Custom Translator models and troubleshoot quotas and errors. For localization teams building batch translation; needs an Azure account and Translator resource.

Calls image and video models such as FLUX, Veo and Seedance through inference.sh's belt CLI to generate images, video, avatars and voiceovers, plus guides for thumbnails, storyboards, press releases and social copy. Needs belt and a free inference.sh account; model calls are billed per use.

Unbabel's machine-translation quality metric: comet-score rates translations per sentence and overall, XCOMET marks error spans and severity, and CometKiwi works without a reference. Good for spot-checking MT. Needs Python 3.8+; models download from Hugging Face, some need a license; GPU helps.

The Docling project's official MCP: converts PDF, Word, PowerPoint and more into structured documents with layout and table detection and OCR for scans, and lets agents build new documents paragraph by paragraph and export Markdown. Local mode needs Python and uv, or use your own Docling Serve.

Rewrites a paper for a target journal: give it 5-8 papers from that journal (plus optional field or lab examples), it builds an editable style guide for your manuscript, then rewrites section by section to the journal's conventions with a change log. PDF input needs a converter such as MinerU.

Shopify's official CLI: scaffold, develop locally and deploy Shopify apps, extensions, Functions and themes, and build and host Hydrogen custom storefronts. Requires Node.js.

A research plugin for Claude Code: commands like /omp:survey, /omp:experiment and /omp:write chain literature review, topic selection, experiments, writing and self-review, with 5 specialized agents and 34 research skills that remember project progress across sessions. Experiments lean toward ML.