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

# Installation

> Install the CLI, the Python SDK, the TypeScript SDK, or the MCP server.

Knowledge Stack itself is a hosted (or self-hosted) service. What you install locally is one of four clients that talk to it — pick the one that matches your workflow.

<CardGroup cols={2}>
  <Card title="kscli" icon="terminal" href="/cli">
    Best for: terminal users, scripts, CI, bulk ingest.
  </Card>

  <Card title="Python SDK — ksapi" icon="python" href="/sdks/python">
    Best for: data pipelines, notebooks, ingestion workers.
  </Card>

  <Card title="TypeScript SDK" icon="js" href="/sdks/typescript">
    Best for: Next.js / Node / Bun / browser apps.
  </Card>

  <Card title="MCP server — ks-mcp" icon="plug" href="/sdks/mcp-server">
    Best for: agents — LangGraph, OpenAI Agents, Claude Desktop, Cursor.
  </Card>
</CardGroup>

## CLI — `kscli`

Requires **Python 3.12+** and [uv](https://docs.astral.sh/uv/).

<Tabs>
  <Tab title="uv (recommended)">
    ```bash theme={null}
    uv tool install kscli
    kscli --version
    ```

    Upgrade later with `uv tool upgrade kscli`.
  </Tab>

  <Tab title="pipx">
    ```bash theme={null}
    pipx install kscli
    ```
  </Tab>

  <Tab title="pip">
    ```bash theme={null}
    pip install kscli
    ```
  </Tab>

  <Tab title="From source">
    ```bash theme={null}
    git clone https://github.com/knowledgestack/ks-cli.git
    cd ks-cli
    uv sync --all-extras --group dev
    ```
  </Tab>
</Tabs>

## Python SDK — `ksapi`

Requires **Python 3.10+**. Generated from `openapi.yaml` — fully typed, sync + async clients.

<CodeGroup>
  ```bash pip theme={null}
  pip install ksapi
  ```

  ```bash uv theme={null}
  uv add ksapi
  ```

  ```bash poetry theme={null}
  poetry add ksapi
  ```
</CodeGroup>

```python theme={null}
from ksapi import KSApi

ks = KSApi(api_key="sk-user-...", base_url="https://api.knowledgestack.ai")
print(ks.users.me())
```

## TypeScript SDK — `@knowledge-stack/ksapi`

Works in Node 18+, Bun, Deno, and modern browsers. Tree-shakeable.

<CodeGroup>
  ```bash npm theme={null}
  npm install @knowledge-stack/ksapi
  ```

  ```bash pnpm theme={null}
  pnpm add @knowledge-stack/ksapi
  ```

  ```bash yarn theme={null}
  yarn add @knowledge-stack/ksapi
  ```

  ```bash bun theme={null}
  bun add @knowledge-stack/ksapi
  ```
</CodeGroup>

```typescript theme={null}
import { KSApi } from "@knowledge-stack/ksapi";

const ks = new KSApi({
  apiKey: process.env.KS_API_KEY,
  baseUrl: "https://api.knowledgestack.ai",
});
console.log(await ks.users.me());
```

## MCP server — `ks-mcp`

Lets any MCP-compatible agent host (Claude Desktop, Cursor, LangGraph, OpenAI Agents) call Knowledge Stack as tools.

```bash theme={null}
uv tool install ks-mcp
```

Then register it with your host — see the [MCP server guide](/sdks/mcp-server) for `claude_desktop_config.json`, Cursor, and LangGraph snippets.

## Verify your install

<CodeGroup>
  ```bash kscli theme={null}
  kscli login --api-key sk-user-...
  kscli whoami
  ```

  ```python Python theme={null}
  from ksapi import KSApi
  ks = KSApi(api_key="sk-user-...")
  print(ks.users.me())
  ```

  ```typescript TypeScript theme={null}
  import { KSApi } from "@knowledge-stack/ksapi";
  const ks = new KSApi({ apiKey: process.env.KS_API_KEY });
  console.log(await ks.users.me());
  ```
</CodeGroup>

If `users.me` returns your user object, you're ready for the [Quickstart](/quickstart).

<Note>
  Don't have an API key yet? [Book a demo](https://www.knowledgestack.ai/book-demo) and we'll provision a sandbox tenant for you.
</Note>

## Self-hosting the server

Running Knowledge Stack itself (not just a client) on your own hardware is covered in the [Quickstart's self-hosted setup](/quickstart#self-hosted-setup) and the [Deployment](/deployment) section.