Install payload
Install payload is broadly covered in current results.
83% (10/12)
Source-backed filter active — add entries to compare trust side by side.
21 results in this view
1 trust signal differs in this sample: Submitter
Signals differ on Submitter — add entries to compare before you install.
Rollout signal scan
Biggest gaps: metadata review, package integrity. 0 entries have 2+ required gaps.
Install payload
Install payload is broadly covered in current results.
83% (10/12)
Adoption queue
3/21 visible results are in hold tier and need mitigation before adoption.
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/agent-device-mcp-server · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/clerk-mcp-server · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/convex-mcp-server · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
skills/convex-nextjs-realtime-apps · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
tools/copilotkit · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/expo-mcp-server · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
skills/expo-skills · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
skills/google-stitch-design-skills · trust review · confidence 67%
Decision confidence
3/21 results are low-confidence and need review before adoption.
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/agent-device-mcp-server · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/clerk-mcp-server · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/convex-mcp-server · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
skills/convex-nextjs-realtime-apps · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
tools/copilotkit · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/expo-mcp-server · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
skills/expo-skills · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
skills/google-stitch-design-skills · trust review
Freshness distribution
Median age 40 days; all 12 scanned entries are within 90 days.
Theme distribution
57% of this view shares the top theme. Leading themes: react, agents, mcp.
79 distinct themes across 21 scanned
Source-backed Claude agent prompt for contributing to the official React Router monorepo using its AGENTS.md guidance for modes, pnpm commands, tests, docs generation, type generation, future flags, and change files.
Open-source full-stack web framework for building web apps entirely in Python, compiling a Python frontend to React and Next.js while keeping state management and event handling in Python, useful for building UIs, dashboards, and tools for AI apps and agents.
MIT-licensed frontend stack for agent-native applications and generative UI, with React, Angular, Vue, React Native, Slack and Teams surfaces, AG-UI protocol support, shared state, human-in-the-loop workflows, backend tool rendering, coding-agent skills, and runtime packages for agent apps.
Official Expo AI agent skills for building, deploying, upgrading, observing, and debugging Expo and React Native apps with Expo Router, EAS, native modules, App Clips, Tailwind, native UI, and EAS Update insights.
Official GreenSock GSAP AI Skills for coding agents that need correct GSAP tweens, timelines, ScrollTrigger, React cleanup, plugins, utilities, framework lifecycle guidance, and animation performance patterns.
Browse and install Magic UI animated React components from Claude — search the library by name or keyword, retrieve full installation details for any entry, and get guided setup instructions — with the official Magic UI MCP server.
Official Java SDK for Model Context Protocol clients and servers, maintained in collaboration with Spring AI, with Java 17+ support, Maven artifacts, synchronous and asynchronous APIs, Reactive Streams, Project Reactor, JDK HttpClient, Servlet transport, JSON binding modules, and conformance tests.
Vercel Labs' official Agent Skills collection for AI coding agents working on Vercel deployments, React and Next.js performance, React Native, web design guidelines, writing guidelines, composition patterns, view transitions, CLI token workflows, and Vercel optimization audits.
Build Convex-backed Next.js App Router applications with typed backend functions, reactive queries, client providers, realtime UI, data imports, and production deployment review.
Official Expo-hosted remote MCP server for connecting Claude and other MCP clients to Expo documentation, Expo SDK guidance, EAS builds, EAS workflows, TestFlight crash and feedback data, React Native DevTools, and simulator automation for Expo projects.
Apache-2.0 reactive Python notebook stored as pure Python for reproducible experiments, SQL-backed data workflows, script execution, app deployment, and AI-assisted editing.
Build React server-state workflows with TanStack Query v5, including query keys, QueryClient setup, cache defaults, mutations, invalidation, hydration, retries, and privacy-aware data handling.
Source-backed Claude agent prompt for contributing to the official TanStack/router monorepo using its AGENTS.md guidance for pnpm, Nx, targeted package tests, React and Solid router packages, TanStack Start, examples, docs, and sandbox-safe execution.
Magic MCP by 21st.dev lets Claude generate polished, production-ready UI components from natural language, returning React and Tailwind code you can drop straight into a project.
The official Convex MCP server, built into the Convex CLI, that lets AI agents introspect and query a Convex deployment — listing tables, paginating data, running deployed functions and read-only one-off queries, reading logs and function specs, and managing environment variables — with production deployments blocked by default as a safety measure.
Get accurate Clerk SDK snippets and implementation patterns directly inside Claude — for authentication flows, Organizations, custom sign-in, B2B SaaS, and more — with the official Clerk remote MCP server.
Agent Skills and plugin packs for Google Stitch design workflows, including code-to-design, design generation, design-system extraction, React and React Native conversion, shadcn/ui guidance, Remotion walkthroughs, and prompt enhancement.
Source-backed Claude agent prompt for contributing to the official elastic/kibana repository using its AGENTS.md guidance for Kibana modules, plugin lifecycle boundaries, server plugin lazy loading, TypeScript style, i18n, Scout, Jest, FTR, scoped type checks, and focused validation.
Source-backed Claude agent prompt for contributing to the official mui/material-ui monorepo using its AGENTS.md guidance, pnpm workspace filters, package build and test commands, component conventions, public error-message rules, API docs generation, visual regression and accessibility checks, and pre-PR checklist.
Official MCP server for agent-device, Callstack's device automation CLI for inspecting, controlling, debugging, recording, and collecting evidence from iOS, Android, TV, macOS, Linux, React Native, Expo, Flutter, and native apps.
Python framework from Stanford NLP for programming language-model systems with signatures, modules, tools, metrics, and optimizers instead of hand-written prompts.