도구

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).

Lets agents mix, master and compose MIDI in REAPER: set up sidechain compression, parallel compression and mastering chains in one step, quantize and humanize MIDI, with every change undoable in REAPER. Needs REAPER, Python 3.10+ and uv; install the bridge script, then run it in REAPER.

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.

Turns one idea into a sparse, wordless white-chalk illustration on an even green board. Picks one of six composition families, generates an image, checks it against a gated QA list and repairs it up to twice. Needs image generation and inspection; otherwise returns the prompt and recipe.

Translates a concept into one spatial event, like orbit or convergence, and renders it as a sparse geometric illustration or poster on matte paper, grayscale and text-free by default. Checks the result against quality gates and regenerates once; falls back to prompt-only output.

Connects to GeoServer's REST API so agents can manage workspaces, data stores, layers and styles, run CQL spatial queries, and access features and render maps via WMS/WFS, for publishing and maintaining map services. Needs a running GeoServer with an admin account, Python 3.10+ and uv.

Ableton Live assistant: create tracks and clips in Arrangement view, batch add, edit and delete notes, load instruments and effects, and record over a time range; note edits can be undone. Needs Live 12 and Node.js 20+, plus the AbletonJS control script installed and enabled in Live.

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+.

Official agent-first CLI from fal: search and run 1,200+ image, video and speech generation models on fal.ai, check parameters and pricing, upload inputs and download results, with structured JSON output. Good for batch image and promo asset generation. Needs a fal.ai API key, billed per use.

Official ListenHub skills: agents turn a topic, article or link into podcasts, explainer videos and slides, and can also do voiceovers, voice cloning, background music and image generation. Needs a ListenHub account (free credits included) and the listenhub CLI.

UK legal research service from i.AI, the UK government's AI incubator, with a remote MCP: semantic search over UK legislation, amendments and explanatory notes. Connect directly, no account. Officially experimental; case law is temporarily disabled and results need a lawyer's review.

Prisma's official skills: the Prisma ORM CLI, Client query API, connection setup for various databases, a v6 to v7 upgrade guide, and deployment workflows for Prisma Postgres and Compute.

Pulumi's official skills: Pulumi program best practices, components and the Automation API, ESC secrets and config, debugging failed pulumi up runs, and migrating from Terraform, CDK, CloudFormation or ARM to Pulumi.

Pulumi's official plugin marketplace: write infrastructure as code in TypeScript, Python, Go and more, migrate from Terraform, CDK, CloudFormation or ARM, and manage ESC secrets and config. Works with both Claude Code and Codex.

Readwise's official CLI: lets agents search articles and highlights saved in Readwise and Reader, save web pages, tag items and organize reading lists, with a read-only mode to prevent accidental changes. Needs Node.js; Readwise is a paid subscription with a 30-day free trial.

42 official AWS skills for healthcare and life sciences: medical coding and terminology mapping, FHIR/HL7 parsing, claims and prior authorization rules, medical imaging, pharmacoepidemiology and genomics, per US standards. Some need local software. Not for clinical decisions; expert review required.

Runway's official plugin: agents batch-generate videos, images, voiceovers and sound effects from one prompt, for ad variations, product videos and multi-shot shorts; also helps developers integrate Runway into apps. Needs a Runway developer account ($10 minimum top-up), an API key and uv.

Patsnap's official patent MCP servers: search 200M+ patents worldwide, check legal status and annuity fees, and run novelty, FTO, valuation and portfolio analyses. Needs a Patsnap Open Platform API key; each service connects separately (the command adds advanced search).

Taps CourtListener's 4M+ US court opinions: search case law by topic, trace citing and cited cases, and parse Bluebook citations; with accounts configured it also queries PACER federal dockets and Clio matters and time entries. Needs Python (uv); a licensed attorney must review results.