mcp-apps-builder
**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns. **READ THIS FIRST** before any MCP server work, including: - Creating new MCP servers - Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) - Debugging MCP server issues or errors - Reviewing MCP server code for quality, security, or performance - Answering questions about MCP development or mcp-use patterns - Making ANY changes to server.tool(), server.resource(), server.prompt(), or widgets This skill contains critical architecture decisions, security patterns, and common pitfalls. Always consult the relevant reference files BEFORE implementing MCP features.
What this skill does
# IMPORTANT: How to Use This Skill
This file provides a NAVIGATION GUIDE ONLY. Before implementing any MCP server features, you MUST:
1. Read this overview to understand which reference files are relevant
2. **ALWAYS read the specific reference file(s)** for the features you're implementing
3. Apply the detailed patterns from those files to your implementation
**Do NOT rely solely on the quick reference examples in this file** - they are minimal examples only. The reference files contain critical best practices, security considerations, and advanced patterns.
---
# MCP Server Best Practices
Comprehensive guide for building production-ready MCP servers with tools, resources, prompts, and widgets using mcp-use.
## ⚠️ FIRST: New Project or Existing Project?
**Before doing anything else, determine whether you are inside an existing mcp-use project.**
**Detection:** Check the workspace for a `package.json` that lists `"mcp-use"` as a dependency, OR any `.ts` file that imports from `"mcp-use/server"`.
```
├─ mcp-use project FOUND → Do NOT scaffold. You are already in a project.
│ └─ Skip to "Quick Navigation" below to add features.
│
├─ NO mcp-use project (empty dir, unrelated project, or greenfield)
│ └─ Scaffold first with npx create-mcp-use-app, then add features.
│ See "Scaffolding a New Project" below.
│
└─ Inside an UNRELATED project (e.g. Next.js app) and user wants an MCP server
└─ Ask the user where to create it, then scaffold in that directory.
Do NOT scaffold inside an existing unrelated project root.
```
**NEVER manually create `MCPServer` boilerplate, `package.json`, or project structure by hand.** The CLI sets up TypeScript config, dev scripts, inspector integration, hot reload, and widget compilation that are difficult to replicate manually.
---
### Scaffolding a New Project
```bash
npx create-mcp-use-app my-server
cd my-server
npm run dev
```
For full scaffolding details and CLI flags, see **[quickstart.md](references/foundations/quickstart.md)**.
---
## Quick Navigation
**Choose your path based on what you're building:**
### 🚀 Foundations
**When:** ALWAYS read these first when starting MCP work in a new conversation. Reference later for architecture/concept clarification.
1. **[concepts.md](references/foundations/concepts.md)** - MCP primitives (Tool, Resource, Prompt, Widget) and when to use each
2. **[architecture.md](references/foundations/architecture.md)** - Server structure (Hono-based), middleware system, server.use() vs server.app
3. **[quickstart.md](references/foundations/quickstart.md)** - Scaffolding, setup, and first tool example
4. **[deployment.md](references/foundations/deployment.md)** - Deploying to Manufact Cloud, self-hosting, Docker, managing deployments
Load these before diving into tools/resources/widgets sections.
---
### 🔐 Adding Authentication?
**When:** Protecting your server with OAuth (WorkOS, Supabase, or custom)
- **[overview.md](references/authentication/overview.md)**
- When: First time adding auth, understanding `ctx.auth`, or choosing a provider
- Covers: `oauth` config, user context shape, provider comparison, common mistakes
- **[workos.md](references/authentication/workos.md)**
- When: Using WorkOS AuthKit for authentication
- Covers: Setup, env vars, DCR vs pre-registered, roles/permissions, WorkOS API calls
- **[supabase.md](references/authentication/supabase.md)**
- When: Using Supabase for authentication
- Covers: Setup, env vars, HS256 vs ES256, RLS-aware API calls
- **[custom.md](references/authentication/custom.md)**
- When: Using any other identity provider (GitHub, Okta, Azure AD, Google, etc.)
- Covers: Custom verification, user info extraction, provider examples
---
### 🔧 Building Server Backend (No UI)?
**When:** Implementing MCP features (actions, data, templates). Read the specific file for the primitive you're building.
- **[tools.md](references/server/tools.md)**
- When: Creating backend actions the AI can call (send-email, fetch-data, create-user)
- Covers: Tool definition, schemas, annotations, context, error handling
- **[resources.md](references/server/resources.md)**
- When: Exposing read-only data clients can fetch (config, user profiles, documentation)
- Covers: Static resources, dynamic resources, parameterized resource templates, URI completion
- **[prompts.md](references/server/prompts.md)**
- When: Creating reusable message templates for AI interactions (code-review, summarize)
- Covers: Prompt definition, parameterization, argument completion, prompt best practices
- **[response-helpers.md](references/server/response-helpers.md)**
- When: Formatting responses from tools/resources (text, JSON, markdown, images, errors)
- Covers: `text()`, `object()`, `markdown()`, `image()`, `error()`, `mix()`
---
### 🎨 Building Visual Widgets (Interactive UI)?
**When:** Creating React-based visual interfaces for browsing, comparing, or selecting data
- **[basics.md](references/widgets/basics.md)**
- When: Creating your first widget or adding UI to an existing tool
- Covers: Widget setup, `useWidget()` hook, `isPending` checks, props handling
- **[state.md](references/widgets/state.md)**
- When: Managing UI state (selections, filters, tabs) within widgets
- Covers: `useState`, `setState`, state persistence, when to use tool vs widget state
- **[interactivity.md](references/widgets/interactivity.md)**
- When: Adding buttons, forms, or calling tools from within widgets
- Covers: `useCallTool()`, form handling, action buttons, optimistic updates
- **[ui-guidelines.md](references/widgets/ui-guidelines.md)**
- When: Styling widgets to support themes, responsive layouts, or accessibility
- Covers: `useWidgetTheme()`, light/dark mode, `autoSize`, layout patterns, CSS best practices
- **[advanced.md](references/widgets/advanced.md)**
- When: Building complex widgets with async data, error boundaries, or performance optimizations
- Covers: Loading states, error handling, memoization, code splitting
---
### 📚 Need Complete Examples?
**When:** You want to see full implementations of common use cases
- **[common-patterns.md](references/patterns/common-patterns.md)**
- End-to-end examples: weather app, todo list, recipe browser
- Shows: Server code + widget code + best practices in context
---
## Decision Tree
```
What do you need?
├─ New project from scratch
│ └─> quickstart.md (scaffolding + setup)
│
├─ OAuth / user authentication
│ └─> authentication/overview.md → provider-specific guide
│
├─ Simple backend action (no UI)
│ └─> Use Tool: server/tools.md
│
├─ Read-only data for clients
│ └─> Use Resource: server/resources.md
│
├─ Reusable prompt template
│ └─> Use Prompt: server/prompts.md
│
├─ Visual/interactive UI
│ └─> Use Widget: widgets/basics.md
│
└─ Deploy to production
└─> deployment.md (cloud deploy, self-hosting, Docker)
```
---
## Core Principles
1. **Tools for actions** - Backend operations with input/output
2. **Resources for data** - Read-only data clients can fetch
3. **Prompts for templates** - Reusable message templates
4. **Widgets for UI** - Visual interfaces when helpful
5. **Mock data first** - Prototype quickly, connect APIs later
---
## ❌ Common Mistakes
Avoid these anti-patterns found in production MCP servers:
### Tool Definition
- ❌ Returning raw objects instead of using response helpers
- ✅ Use `text()`, `object()`, `widget()`, `error()` helpers
- ❌ Skipping Zod schema `.describe()` on every field
- ✅ Add descriptions to all schema fields for better AI understanding
- ❌ No input validation or sanitization
- ✅ Validate inputs with Zod, sanitize user-provided data
- ❌ Throwing errors instead of returning `error()` helper
- ✅ Use `error("message")` for graceful error responses
### Widget Development
- ❌ Accessing `props` without checking `isPending`
- ✅ Always check `if (isPending) return <Loading/>`
- ❌ Widget handles server staRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.