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

# Quickstart

> Connect your AI tool to Condense MCP and list your workspaces in four steps.

You need an AI tool that supports remote MCP servers and a Condense account with access to at least one environment. See [Before you connect](https://docs.condense.io/condense/v3.0.0/mcp/overview.md#before-you-connect) if you are not sure.

**1. Copy the server URL**

```text theme={null}
https://app.condense.io/api/mcp_servers/mcp
```

The URL is the only thing you give your AI tool. There is no key to create.

**2. Add it to your AI tool**

In Claude Code, for example, run:

```bash theme={null}
claude mcp add --scope project --transport http condense "https://app.condense.io/api/mcp_servers/mcp"
```

For every other tool, see [Connect your AI tool](https://docs.condense.io/condense/v3.0.0/mcp/connect-your-ai-tool.md).

**3. Sign in and approve**

Start the sign-in from your AI tool. In Claude Code, run `claude`, type `/mcp`, select `condense` and choose **Authenticate**.

Your browser opens a Condense page. Choose an environment, review the permissions and select **Accept**. See [Sign in and approve access](https://docs.condense.io/condense/v3.0.0/mcp/sign-in-and-approve-access.md).

**4. Ask a question**

Open your AI tool's chat and ask:

```text theme={null}
List all Condense workspaces I can access.
```

## What good looks like

Your AI tool calls the `get_all_workspaces` tool and shows the workspaces you can access in the environment you chose. Workspaces you are not authorized for are not shown.

If you see an error, or the list is empty when it should not be, go to [Verify and reconnect](https://docs.condense.io/condense/v3.0.0/mcp/verify-and-reconnect.md) or [Errors and troubleshooting](https://docs.condense.io/condense/v3.0.0/mcp/errors-and-troubleshooting.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.