mcp-apps
This skill provides guidance for building MCP Apps, the official io.modelcontextprotocol/ui extension for interactive HTML interfaces inside MCP hosts. This skill should be used when the user asks to "create an MCP App", "add UI to an MCP tool", "build interactive MCP", "ui:// resource", "sandboxed iframe MCP", "interactive chat UI", "embed UI in chat", "MCP tool with interface", or needs capability negotiation, resource CSP, app-only tools, host lifecycle, or progressive text fallbacks.

Install the complete plugin to include its agents, hooks, commands, and runtime context.
- PUBLISHER
- b-open-io
- RELATIONSHIP
- authored
- VERSION
- 0.1.2
- BENCHMARK
- unknown
Install bOpen Mcp
The complete plugin is the supported path. It preserves everything the publisher designed to work alongside this skill.
Codex
VERIFIEDGrok Build
VERIFIED- This is the grok CLI, not Grok Bot.
- grok plugin details mcp-dev
Grok Bot
GUIDED SETUP- Paste this request into your Bot’s conversation. It will report what it can add.
OpenCode
VERIFIED- Paste into OpenCode. Restart after installation.
- Includes native agents, commands, skills and supported hooks/MCP. HammerTime uses bounded follow-up turns in persistent sessions.
Install only this skill
Use this narrower path only when you intentionally want the portable SKILL.md without the plugin’s surrounding capabilities.
Skills CLI
VERIFIED- Installs only the portable skill; it omits plugin hooks, agents, commands, apps/MCP configuration, and unlisted companion skills.
Grok Bot
GUIDED SETUP- Paste into your Bot’s conversation. Once saved, use / to select the skill.
Trace it to the source.
- DISTRIBUTED SOURCE
- modules/mcp-dev/skills/mcp-apps/SKILL.md ↗
- UPSTREAM SOURCE
- No separate upstream declared
- DISTRIBUTED DIGEST
- sha256:f0afb4e4d89eae0349e578270821f959c5f8761dc8302c1db6d426ed1c302664
- LOCK HASH
- Not applicable
Companion skills
No required companion skills are declared.
Agents using this skill

Satchmo
Agent architecture specialist. Use this agent when the user asks to "design an agent", "wire up tool-calling", "add memory to my agent", "set up agent routing", "implement delegated signup", "support auth.md", or "integrate ID-JAG". Covers evals, resilient chat UIs, and delegated agent auth. Not for deploying a built agent to hosting or wiring its cron and sandbox (use devops), authoring individual skills or commands (use prompt-engineer), or auditing skill accuracy (use trainer).

Ridd
UI and interface design agent. Use this agent when the user asks to "design a component", "create UI", "style a page", "set up shadcn", "implement dark mode", "review UI accessibility", "create a mockup", "design a game HUD", "build a TV app interface", or "add controller navigation". Covers design systems, ten-foot UI, and Pencil mockups. Not for performance work (use optimizer) or 3D scenes (use creative-developer).

Kris
Creative 3D web developer for Three.js and React Three Fiber, including diegetic and world-space UI. Use this agent when the user asks to "create a 3D scene", "build a Three.js demo", "write a shader", "add physics to a scene", "build a WebGL prototype", or "optimize 3D performance". Covers R3F, Drei, GLSL, TSL, and 3D asset pipelines. Not for 2D interface design (use designer).

Orbit
MCP specialist. Use this agent when the user asks to "set up an MCP server", "build an MCP App", "connect Claude Code to my database via MCP", "fix this MCP connection error", or "publish my MCP server to npm". Covers MCP Apps, JSON Render, PostgreSQL/Redis/MongoDB/GitHub/Vercel servers, and the Tool Search Tool. Not for general third-party API integrations (use integration-expert) or agent tool-calling logic (use agent-builder).

Maxim
Third-party service integration specialist. Use this agent when the user asks to "wire up this webhook", "integrate with this API", "sync data from X on a schedule", or "send transactional emails" — with signature verification, rate limiting, and error handling. Not for money-movement integrations (use payments) or MCP server setup (use mcp).
Share this skill.
Pass the canonical page to a teammate or keep it close for later.
cost-tracking
This skill should be used when tracking API spend, analyzing billing data, monitoring service costs, running budget reports, or optimizing agent spend across Anthropic, Vercel, Railway, and other platforms. Invoke when asked about "cost tracking", "billing analysis", "spend report", "API costs", "usage monitoring", "budget vs actual", "cost optimization", or "which agents cost the most".