
Augments
OfficialProvides real-time documentation, type signatures, and code examples for 90+ frameworks and any npm package. Returns context-aware formatting with types, prose explanations, and examples based on your query intent.
Real-time framework documentation provider for 90+ frameworks
What it does
- Search framework documentation with concept synonyms
- Get detailed framework info with types and examples
- Retrieve code examples for specific patterns
- Analyze code compatibility across frameworks
- Check for framework documentation updates
- Get multi-framework context for development tasks
Best for
About Augments
Augments is an official MCP server published by augmnt that provides AI assistants with tools and capabilities via the Model Context Protocol. Augments — real-time framework documentation for 90+ frameworks. Access instant, up-to-date guides, examples, and API re It is categorized under developer tools. This server exposes 12 tools that AI clients can invoke during conversations and coding sessions.
How to install
You can install Augments in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server supports remote connections over HTTP, so no local installation is required.
License
Augments is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Tools (12)
List all available frameworks, optionally filtered by category. Args: category: Filter by category (web, backend, mobile, ai-ml, design, tools) Returns: List of framework information including name, category, and description
Search for frameworks by name, keyword, or feature. Args: query: Search term to match against framework names and features Returns: Ranked list of matching frameworks with relevance scores
Get detailed information about a specific framework. Args: framework: Framework name Returns: Detailed framework information or error message
Retrieve comprehensive documentation for a specific framework. Args: framework: Framework name (e.g., 'react', 'tailwind', 'laravel') section: Specific documentation section (e.g., 'installation', 'configuration') use_cache: Whether to use cached content (default: True) Returns: Formatted documentation content with examples and best practices
Get code examples for specific patterns within a framework. Args: framework: Framework name pattern: Specific pattern (e.g., 'components', 'routing', 'authentication') Returns: Code examples with explanations and best practices

A next-generation framework documentation provider for Claude Code via Model Context Protocol (MCP). Returns types + prose + examples with context-aware formatting for any npm package — not just curated ones.
mcp-name: dev.augments/mcp
What's New in v5
Version 5.0 closes the gap with context7 by adding prose documentation, README fallback, concept search, and intent-aware formatting — while keeping the type-signature accuracy that made v4 unique.
| v4 | v5 |
|---|---|
| Type signatures only | Types + prose + examples |
| ~20 curated frameworks | Any npm package (auto-discovery) |
| Keyword-only search | Concept synonyms ("state" → useState, createStore, atom) |
| One-size-fits-all format | Intent-aware (how-to vs reference vs migration) |
| 7 tools (4 legacy) | 3 focused tools |
What You Get Now
Query: "how to use zustand"
→ Intent: howto
→ Code examples first, then prose explanation, then brief signature
Query: "useEffect signature"
→ Intent: reference
→ Full signature, parameters, return type, related types, 1 example
Query: "ioredis set"
→ README fallback provides examples for uncurated packages
Quick Start
Option 1: Hosted MCP Server — project-local (Recommended)
# Add the hosted MCP server (available in current project only)
claude mcp add --transport http augments https://mcp.augments.dev/mcp
# Verify configuration
claude mcp list
Option 2: Hosted MCP Server — user-wide
# Add the hosted MCP server (available across all projects)
claude mcp add --transport http --scope user augments https://mcp.augments.dev/mcp
# Verify configuration
claude mcp list
Option 3: Using Cursor
{
"mcpServers": {
"augments": {
"transport": "http",
"url": "https://mcp.augments.dev/mcp"
}
}
}
Usage
# Get API context with prose + examples (recommended first tool to try)
@augments get_api_context query="useEffect cleanup" framework="react"
# How-to format — examples first
@augments get_api_context query="how to use zustand"
# Reference format — full signature first
@augments get_api_context query="zod object signature"
# Search for APIs by concept (synonym-aware)
@augments search_apis query="state management"
# Get version information and breaking changes
@augments get_version_info framework="react" fromVersion="18" toVersion="19"
Tools
| Tool | Description |
|---|---|
get_api_context | Primary tool. Returns API signatures, prose documentation, and code examples for any npm package. Handles natural language queries with intent detection. |
search_apis | Search for APIs across frameworks by keyword or concept. Supports synonym expansion ("state" matches useState, createStore, atom, etc). |
get_version_info | Get npm version info, compare versions, and detect breaking changes. |
Architecture
flowchart TD
A["Query: 'how to use useEffect cleanup'"] --> B
B["Intent Detection → howto<br/>Query Parser → react / useEffect"]
B --> C["Type Fetcher<br/>CDN racing · npm metadata · @types"]
B --> D["Example Extractor<br/>GitHub docs · README fallback · Auto-discovery"]
C --> E["Type Parser<br/>Signatures · Parameters · Related types"]
D --> F["Prose Extractor<br/>Section scoring · Paragraph extract · 2000 char budget"]
E --> G["Intent-Driven Formatter (howto)<br/>→ Examples first, prose, brief signature<br/>→ ~500-2000 tokens, 10KB max"]
F --> G
Source Structure
src/
├── core/ # Core modules
│ ├── query-parser.ts # Parse natural language → framework + concept
│ ├── type-fetcher.ts # Fetch .d.ts + README from npm/unpkg/jsdelivr
│ ├── type-parser.ts # Parse TypeScript, extract signatures, synonym search
│ ├── example-extractor.ts # Fetch examples from GitHub docs + auto-discovery
│ └── version-registry.ts # npm registry integration
├── tools/v4/ # MCP tools
│ ├── get-api-context.ts # Primary tool (types + prose + examples)
│ ├── search-apis.ts # Cross-framework API search
│ └── get-version-info.ts # Version comparison
└── server.ts # MCP server (3 tools)
Key Features
Concept Synonyms
"state management" matches useState, useReducer, createStore, atom, signal, ref, reactive, writable, store. Eight concept clusters cover state, form, fetch, animation, routing, auth, cache, and effect patterns.
README Fallback
For the 99%+ of npm packages without curated documentation sources, augments fetches README.md from the CDN and extracts concept-relevant code blocks and prose.
Auto-Discovery
When no curated doc source exists, augments parses the npm repository field, identifies the GitHub repo, and probes for docs/, documentation/, doc/, or README.md.
Intent-Aware Formatting
| Intent | Trigger | Format |
|---|---|---|
howto | "how to", "example of", "guide" | Examples → prose → brief signature |
reference | "signature", "types", "parameters" | Full signature → related types → 1 example |
migration | "migrate", "upgrade", "breaking" | Prose → signature → examples |
balanced | Default | Signature → prose → examples |
Coverage
Any npm Package
Every npm package is supported out of the box — no curation or configuration needed. Augments resolves documentation automatically through three layers:
- TypeScript types — bundled (
"types"in package.json) or DefinitelyTyped (@types/*) - Auto-discovered docs — parses the npm
repositoryfield, finds the GitHub repo, and probesdocs/,documentation/,doc/directories - README fallback — extracts concept-relevant code blocks and prose directly from
README.md
This means augments works with the entire npm ecosystem (~2.5M packages), not just a curated subset.
Enhanced Results for Popular Frameworks
22 frameworks have curated doc sources for richer examples: React, Next.js, Vue, Prisma, Zod, Supabase, TanStack Query, tRPC, React Hook Form, Framer Motion, Express, Zustand, Jotai, Drizzle, SWR, Vitest, Playwright, Fastify, Hono, Solid, Svelte, Angular, Redux
Barrel Export Handling
Special sub-module resolution for: React Hook Form, TanStack Query, Zustand, Jotai, tRPC, Drizzle ORM, Next.js
Self-Hosting
Deploy to Vercel
Local Development
# Clone and install
git clone https://github.com/augmnt/augments-mcp-server.git
cd augments-mcp-server
npm install
# Run development server
npm run dev
# Run tests
npm test
# Type check
npm run type-check
# Build
npm run build
How v5 Compares to Context7
| Aspect | Context7 | Augments v5 |
|---|---|---|
| Source | Parsed prose docs | TypeScript definitions + prose + README |
| Accuracy | Docs can be wrong | Types must be correct, prose supplements |
| Context size | ~5-10KB chunks | ~500-2000 tokens (intent-aware) |
| Coverage | Manual submission | Any npm package (auto-discovery) |
| Format | One-size-fits-all | Intent-aware (how-to vs reference) |
| Search | Keyword match | Concept synonyms + keyword |
| Freshness | Crawl schedule | On-demand from npm |
Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Make your changes
- Run tests:
npm test - Submit a pull request
License
MIT License - see LICENSE for details.
Support
Built for the Claude Code ecosystem | Version 5.0.0
Alternatives
Related Skills
Browse all skillsUI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools. Use for creating design systems, maintaining visual consistency, and facilitating design-dev collaboration.
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".
Master API documentation with OpenAPI 3.1, AI-powered tools, and modern developer experience practices. Create interactive docs, generate SDKs, and build comprehensive developer portals. Use PROACTIVELY for API documentation or developer portal creation.
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`.
Guide for building TypeScript CLIs with Bun. Use when creating command-line tools, adding subcommands to existing CLIs, or building developer tooling. Covers argument parsing, subcommand patterns, output formatting, and distribution.
Integrate Vercel AI SDK applications with You.com tools (web search, AI agent, content extraction). Use when developer mentions AI SDK, Vercel AI SDK, generateText, streamText, or You.com integration with AI SDK.