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

# MCP Server

> Drive the Noxus platform from any MCP-compatible client (Claude, Cursor, your own agents)

## What it is

Noxus runs a hosted **[Model Context Protocol](https://modelcontextprotocol.io) (MCP) server**. It exposes the platform's capabilities — workflows, agents, conversations, knowledge bases, tables, sandboxes, deployments and more — as MCP **tools** that any MCP-compatible client can call.

Point Claude Desktop, Claude Code, Cursor, or your own agent at it, authenticate with a Noxus API key, and the model can list your workflows, run them, search a knowledge base, query a data table, or create an agent — all as native tool calls, no glue code.

<CardGroup cols={2}>
  <Card title="Remote, hosted" icon="cloud">
    A single streamable-HTTP endpoint — nothing to install or run locally.
  </Card>

  <Card title="Your API key = your access" icon="key">
    Authenticate with a workspace API key; tools are gated by that key's permissions.
  </Card>

  <Card title="Same surface as the SDK" icon="layers">
    Backed by the same platform APIs as the Python SDK, so behavior matches.
  </Card>

  <Card title="Model-native" icon="robot">
    Tools carry typed schemas, so models call them reliably without prompt glue.
  </Card>
</CardGroup>

## Connection details

|               |                                              |
| ------------- | -------------------------------------------- |
| **Endpoint**  | `https://backend.noxus.ai/mcp`               |
| **Transport** | Streamable HTTP                              |
| **Auth**      | `Authorization: Bearer <YOUR_NOXUS_API_KEY>` |
| **Scope**     | The workspace the API key belongs to         |

<Info>
  Self-hosted / on-prem deployments serve the same MCP server at
  `https://<your-backend-host>/mcp`. Use that URL in place of
  `backend.noxus.ai/mcp` below.
</Info>

## Authentication

The server takes your **Noxus API key** as a bearer token. It's the same key you use for the [SDK](/sdk/concepts/authentication) and [REST API](/api-reference/introduction) — create one in the Noxus UI under **Settings → Organization → Workspaces → (pick a workspace) → API Keys**.

Every tool call runs **as that key**, in its workspace, and is subject to the key's permissions. A read-only key can list and read but not create or delete; a key without the `sandboxes:run` permission can't spin up sandboxes. This is the same permission model as the REST API — see [Authentication](/sdk/concepts/authentication).

## MCP vs. SDK vs. REST

All three hit the same platform. Pick by how you're building:

<CardGroup cols={3}>
  <Card title="MCP" icon="plug">
    You want an **LLM/agent** to operate Noxus as tools (Claude, Cursor, a custom agent). No code — the model calls tools directly.
  </Card>

  <Card title="Python SDK" icon="python">
    You're writing a **Python program** and want typed resources, pagination helpers, and streaming. See the [SDK](/sdk/introduction).
  </Card>

  <Card title="REST API" icon="code">
    You're in **another language** or wiring a webhook/integration. See the [API reference](/api-reference/introduction).
  </Card>
</CardGroup>

## Next steps

<CardGroup cols={2}>
  <Card title="Connect a client" icon="link" href="/sdk/mcp/connecting">
    Config for Claude Desktop, Claude Code, Cursor, and generic MCP clients.
  </Card>

  <Card title="Available tools" icon="wrench" href="/sdk/mcp/tools">
    The full catalog of tools the server exposes, by domain.
  </Card>
</CardGroup>

<Note>
  Looking to give **one of your Noxus agents** access to an *external* MCP server
  (GitHub, Linear, Notion…)? That's the reverse direction — configured per-agent
  as an MCP tool. See the agent tools documentation.
</Note>