mcp-ui is a software development kit for delivering interactive web interfaces alongside AI tool results through the Model Context Protocol. Developers use its server and client packages to create UI resources and let compatible hosts fetch and render them.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/mcp-ui-org/mcp-ui/copilot-instructionsgit clone --depth 1 https://github.com/MCP-UI-Org/mcp-uiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/mcp-ui-org/mcp-ui/copilot-instructions)<a href="https://agentmods.dev/instructions/mcp-ui-org/mcp-ui/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/mcp-ui-org/mcp-ui/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01709 | $0.01709 |
| Opus 5 | $0.00855 | $0.00855 |
| Sonnet 5 | $0.00342 | $0.00342 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade B, and why
mcp-ui copilot-instructions.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Install Ruby 3.x and bundler: `sudo apt-get install -y ruby ruby-dev build-essential && sudo gem install bundler` How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP-UI Development Instructions
ALWAYS follow these instructions first and fallback to additional search and context gathering only if the information here is incomplete or found to be in error.
MCP-UI is a Model Context Protocol UI SDK monorepo providing TypeScript and Ruby SDKs for building MCP enabled applications with interactive UI components. The repository includes client SDKs, server SDKs, documentation, and examples.
Working Effectively
Bootstrap and Build (CRITICAL - Set 60+ minute timeouts)
- Install Node.js 22.x and pnpm 9+:
npm install -g pnpm - Install Ruby 3.x and bundler:
sudo apt-get install -y ruby ruby-dev build-essential && sudo gem install bundler - Clone repository:
git clone https://github.com/idosal/mcp-ui.git && cd mcp-ui - Install dependencies:
pnpm install-- takes ~60 seconds. NEVER CANCEL. - Build all packages:
pnpm build-- takes ~15 seconds. NEVER CANCEL. Set timeout to 120+ seconds. - Build documentation:
pnpm docs:build-- takes ~17 seconds. NEVER CANCEL. Set timeout to 180+ seconds.
Testing (CRITICAL - Set 30+ minute timeouts)
- Run TypeScript tests:
pnpm test:ts-- takes ~6 seconds. NEVER CANCEL. Set timeout to 300+ seconds. - Run Ruby tests:
pnpm test:ruby-- takes ~1 second. NEVER CANCEL. Set timeout to 300+ seconds. - Run all tests:
pnpm test-- combines TypeScript and Ruby tests. NEVER CANCEL. Set timeout to 300+ seconds. - Run with coverage:
pnpm coverage-- NEVER CANCEL. Set timeout to 600+ seconds.
Code Quality (Always run before committing)
- Lint code:
pnpm lint-- takes ~2.4 seconds. Uses ESLint with TypeScript parser. - Fix linting issues:
pnpm lint:fix - Format code:
pnpm format-- Uses Prettier with single quotes, trailing commas, 100 char width.
Development Workflow
- Run TypeScript SDKs in development:
pnpm dev-- starts all TypeScript package dev servers in parallel. - Run docs in development:
pnpm docs:dev-- starts VitePress dev server. - Preview builds:
pnpm preview-- preview built packages.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 141 lines · 1,709 tokens per session scan B 03fe01b1ed26
mcp-ui copilot-instructions.md is an instructions file published in the GitHub repository MCP-UI-Org/mcp-ui (5,125 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,709 tokens to every session, about $0.0085 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
tool-ui CLAUDE.md
Claude Code instructions for assistant-ui/tool-ui, covering tool ui, commands, tooling, stack and architecture.
tool-ui AGENTS.md
AGENTS.md instructions for assistant-ui/tool-ui, covering agents.md, cursor cloud specific instructions, project overview, running services and commands reference.
platypus CLAUDE.md
Claude Code instructions for willdady/platypus, covering project overview, setup & commands, monorepo layout, known constraints and documentation.
dile-components AGENTS.md
AGENTS.md instructions for Polydile/dile-components, covering development guidelines for dile components, repository overview, packages, documentation site and demos.
OpenClaw-Admin AGENTS.md
Instructions for itq5/OpenClaw-Admin, covering 仓库协作指南, 项目结构与模块组织, 构建、测试与开发命令, 代码风格与命名规范 and 测试要求.
switchai CLAUDE.md
Claude Code instructions for US1929/switchai, covering claude.md, switchai — ai agent per cambio fornitore energia (italia), panoramica, comandi essenziali and sviluppo locale (servono entrambi i processi).