> ## Documentation Index
> Fetch the complete documentation index at: https://smithery.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Smithery is the largest open registry for connecting AI agents to the outside world — search the web, query databases, control browsers, reach into business tools, and much more.

## What can I do with Smithery?

Smithery connects your AI agent to a growing catalog of tools and integrations — and lets you publish your own for others to use. A few popular ones:

* [Exa](https://smithery.ai/servers/exa) - Search the live web, access LinkedIn profiles, do deep research, and more
* [Context7](https://smithery.ai/servers/@upstash/context7-mcp) - Reference the latest docs for most major SDKs and frameworks directly in Cursor or Claude Code
* [Browserbase](https://smithery.ai/servers/@browserbasehq/mcp-browserbase) - Control a remote web browser using [Stagehand](https://stagehand.dev)

<Card title="How does Smithery work?" icon="library-big" href="/concepts/what_is_mcp">
  Under the hood, Smithery speaks the [Model Context Protocol](https://modelcontextprotocol.io/docs/getting-started/intro) (MCP). Learn more in our concepts section.
</Card>

## Why Smithery?

Whether you're building chatbots, background agents, or AI copilots, Smithery handles the messy parts of plugging agents into external services:

* **Zero OAuth configuration** — No redirect URIs, client IDs, or secrets to manage
* **Automatic token refresh** — Credentials stay valid without manual intervention
* **Secure credential storage** — Encrypted, write-only storage for API keys and tokens
* **Stateless for you** — Connection lifecycle managed automatically

## Quickstarts

<CardGroup>
  <Card title="Connect tools to your agent" icon="plug-zap" href="/use/connect">
    Add integrations to your app with managed OAuth and credentials
  </Card>

  <Card title="Publish an integration" icon="rocket" href="/build/publish">
    Publish your MCP server to Smithery for distribution and observability
  </Card>
</CardGroup>

## LLM-Friendly Docs

The Smithery documentation is available in multiple LLM-friendly formats:

### MCP Server

The Smithery docs are accessible via MCP at `https://smithery.ai/docs/mcp`. You can also use the [Context7 MCP server](https://smithery.ai/servers/@upstash/context7-mcp) to search the Smithery documentation.

### Agent Scaffolds

Reference implementations for building agents with Smithery:

* [Basic Scaffold](https://github.com/smithery-ai/sdk/blob/main/examples/basic-server/AGENTS.md) - Build basic MCP servers
* [ChatGPT App](https://github.com/smithery-ai/sdk/blob/main/examples/open-ai-hello-server/AGENTS.md) - Build ChatGPT apps

### Markdown Format

Any page can be accessed as markdown by appending `.md` to the URL. For example, this page becomes `https://smithery.ai/docs/index.md`. You can also copy any page as markdown directly from the documentation.