By mctx-ai
Get accurate answers about mctx and MCP servers from live docs, not outdated training data. Look up deployment steps, payouts, pricing, or framework questions instantly. Works with Claude Code, Cursor, Codex, and any MCP client. Coverage: server framework, deployment, environment variables, subscriptions, payouts, pricing, tools, resources, transports, authentication, versioning. Questions you can ask: "How do I define a tool with input validation?" "What does mctx need in package.json?" "How do I set up payouts?" "What's the difference between ready and live status?" "How does the 80/20 split work?" "Why did my deployment fail?" "What MCP resources and tools are available?"
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
External network access
Connects to servers outside your machine
The official mctx plugin marketplace for Claude Code
Add the mctx marketplace to Claude Code, then install any AI App in seconds.
Step 1 — Add the marketplace
/plugin marketplace add https://mctx.ai/marketplace.json
Step 2 — Install an AI App
/plugin install {slug}@mctx
Replace {slug} with the name of the AI App you want to use.
When you install an mctx AI App:
Visit mctx.ai to learn more about the platform and subscribe to AI Apps.
Need help? The docs cover everything from installation to managing your subscriptions.
The channel plugin bridges real-time events from mctx-hosted MCP servers into your Claude Code session. When an MCP server calls server.emit(), the event arrives in your session as a channel notification — no polling from Claude's side, no manual checking.
Install the channel plugin
/plugin install channel@mctx
Start with channels enabled
claude --dangerously-load-development-channels plugin:channel@mctx
On first launch the plugin opens your browser for mctx authentication. After that, it automatically discovers your channel-enabled subscriptions and starts delivering events.
Events arrive as <channel> tags with provenance metadata:
<channel source="mctx-channel" server_id="my-game" event_type="game_event">
[mctx/my-game] game_event: You entered a dark cave. Exits: north, east.
</channel>
Requires Claude Code v2.1.80+ and an mctx account with active subscriptions to channel-enabled servers.
If you host an MCP server on mctx, enabling Claude Code publishing in your server dashboard automatically lists it in this marketplace. No extra steps required.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub mctx-ai/claude-plugins --plugin helpCentralized note store across AI clients: Claude, ChatGPT, Cursor, Codex, Windsurf. Save in one client, access in another instantly. Across devices — phone, desktop, everywhere. Cross-session context: 'catch me up' surfaces plans and findings from any prior session. AES-256-GCM encryption at rest, per-user key isolation. Soft delete with 30-day recovery window. Pin notes to exempt from cleanup and prioritize. Tag notes for categorization and filtering ('tag: auth'). Your mctx account is your identity — instant access from any AI tool.
Personal todo list that persists across sessions. Create, update, complete, reorder, and delete todos. Todos are private to your mctx account. Call status first in every new session to see what's pending.
Play a legendary text adventure by talking to your AI — no commands to memorize. The Hidden Empire puts a full underground world of puzzles, treasures, and trolls inside your conversation. Speak naturally: say 'head north,' 'grab the lantern,' or 'what am I carrying?' and your AI handles the rest. Execute multi-move plans in one shot, undo mistakes instantly, and save up to 20 named playthroughs you can resume from any session. Based on the MIT-licensed Zork I source, rebuilt from the ground up for AI-native play.
Study the Bible in its original languages, trace themes across both testaments, and compare five translations — all in one conversation. Ask any question about what Scripture says and get grounded, cited answers: What does the Bible say about suffering? Topical search surfaces Job as the Bible's principal witness on suffering (with explanations of why it matters and suggested starting passages), Psalms on lament, Romans on justification — whole books and narratives alongside individual verses. What is the Hebrew word behind lovingkindness in Psalm 23? Compare how KJV and WEB translate John 3:16. Trace the word grace through Paul's letters. Covers 155,510 verses across KJV, WEB, ASV, YLT, and Darby with 606,140 cross-references, 17,543 Strong's entries, BDB and Thayer lexicon definitions, and Nave's 5,319 topical categories.
Build complete Apps with our framework — study or fork this reference implementation. Covers all @mctx-ai/app patterns: tool types (sync string, object return, generators, LLM sampling), resource URIs (static, dynamic templates), prompt formats (single-message, multi-message), tool annotations (readOnly, destructive, openWorld, idempotent), structured logging, environment variables, and test coverage. The whoami tool demonstrates user identity via ctx.userId. Includes setup.sh for quick template generation.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review