# Agora MCP (/en/introduction/agora-mcp)

> For AI agents: see the complete documentation index at [llms.txt](/llms.txt).

Install Agora MCP when you want your assistant to check the latest Agora docs before it writes or changes code. Use it to confirm current SDK methods, parameters, quickstarts, and product or platform differences while you build or debug.

This is most useful when documentation freshness is the risky part of the task. If you also want help choosing the right Agora workflow or starter, add [Agora Skills](/en/introduction/agora-skills).

## Install the MCP server

`Agora MCP` is included when you install [Agora Skills](/en/introduction/agora-skills), but you can also install the MCP server on its own:

```text
https://mcp.agora.io
```

Agora MCP is available only in coding tools where you install or configure it. A regular browser-based chat session does not connect to this server automatically.

**Cursor**

Add the following JSON to your MCP configuration:

```json
{
  "mcpServers": {
    "agora-docs": {
      "url": "https://mcp.agora.io"
    }
  }
}
```

**Claude Code**

```bash
claude mcp add --transport http agora-docs https://mcp.agora.io
```

**Codex**

```bash
codex mcp add --url https://mcp.agora.io agora-docs
```

**Gemini CLI**

```bash
gemini mcp add --transport http agora-docs https://mcp.agora.io
```

**Manual installation**

Add `https://mcp.agora.io` to your MCP client and use `http` or `Streamable HTTP` transport if the client asks for a transport type.

## Check the available tools

The server supports searches across Agora product guides and SDK API references.
Some tools also expose filter discovery.

Your MCP client retrieves the tool catalog through `tools/list`.
Use the returned names, descriptions, and input schemas when selecting tools and preparing arguments.
Supply every required field using the declared types. Tool availability and parameter types can change with the server.

Include the product, platform, and task in each search.
Open returned documentation URLs when search excerpts do not contain the full answer.
For a guide on `docs.agora.io`, append `.md` to read its Markdown content.

If a tool is unavailable, refresh the tool list before selecting another tool.
If MCP is unavailable or returns no useful content, use the fallback resources below.

## Start with a prompt

Install the server in your coding tool, then ask your assistant to search Agora docs before it writes code. Include the Agora product, the target platform, and the task type in the same prompt.

```text
Use Agora MCP to find the current web quickstart for Conversational AI and explain the minimum setup for a browser voice demo.
```

## Make docs lookup part of the workflow

If your repository includes `AGENTS.md` or similar instructions, tell your assistant to prefer Agora MCP for product-specific lookups. That turns docs checks into a normal part of the workflow instead of an optional extra step.

If your MCP client is not available, these fallback resources still help:

- Use `https://docs.agora.io/llms.txt` as the lightweight documentation index. Its entries link directly to Markdown pages.
- Append `.md` to a documentation URL to read that page as Markdown. For example, use `https://docs.agora.io/en/ai/get-started/quickstart.md`.
- Use `https://docs.agora.io/llms-full.txt` only for offline indexing or bulk processing. It is too large to use as the default context for an interactive assistant.
