> For clean Markdown of any page, append `.md` to the page URL.
> For a complete documentation index, see https://docs.sarvam.ai/llms.txt.
> For full documentation content in one file, see https://docs.sarvam.ai/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server.

# Context7

> Pull up-to-date Sarvam AI documentation into Claude Code, Cursor, Windsurf, and other AI clients through Context7, the Sarvam docs are pre-indexed, no setup on our side required.

[Context7](https://context7.com) is a documentation index that AI coding assistants query through MCP to get current, version-accurate docs while you code. The Sarvam docs are indexed there, so any assistant with the Context7 MCP server connected can pull them on demand, no Sarvam-specific configuration needed.

## Library ID

The Sarvam documentation is available under the library ID:

```text
/websites/sarvam_ai
```

You can browse the index directly at [context7.com/websites/sarvam\_ai](https://context7.com/websites/sarvam_ai).

## Setup

Install the Context7 MCP server in your client (see the [Context7 setup guide](https://github.com/upstash/context7) for all clients):

#### Cursor / Claude Code (mcp.json)

```json
{
  "mcpServers": {
    "context7": {
      "command": "npx",
      "args": ["-y", "@upstash/context7-mcp"]
    }
  }
}
```

## Usage

Once connected, reference the library in your prompt:

> "Use library `/websites/sarvam_ai`. Write a Python script that transcribes `audio.wav` with the latest Sarvam speech-to-text model."

The assistant fetches the relevant Sarvam doc pages through Context7 and writes code against the current API.

## Context7 vs. the Sarvam docs MCP server

Both give assistants live access to the docs. Use whichever fits your setup:

|               | Context7                                     | [Sarvam docs MCP server](/api/developer-tools/mcp) |
| ------------- | -------------------------------------------- | -------------------------------------------------- |
| **Best when** | You already use Context7 for other libraries | You want a dedicated Sarvam docs search tool       |
| **Setup**     | One MCP server covers many libraries         | One MCP server per docs site                       |
| **Source**    | Context7's index of docs.sarvam.ai           | Ask Fern search over the live docs                 |

## Related pages

* [MCP Server](/api/developer-tools/mcp)
* [llms.txt & Markdown docs](/api/developer-tools/llms-txt)
* [Agent Skills](/api/developer-tools/agent-skills)

> Pull up-to-date Sarvam AI documentation into Claude Code, Cursor, Windsurf, and other AI clients through Context7, the Sarvam docs are pre-indexed, no setup on our side required.