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

# Claude Code

> Add the Glasser MCP server to Claude Code and sign in.

Use this guide to connect Claude Code directly to Glasser. If you prefer the CLI workflow,
follow [Set up with Skill](/docs/setup-skill/claude-code).

<Steps>
  <Step title="Add the server">
    With Claude Code installed, run this in your terminal:

    ```bash theme={null}
    claude mcp add --transport http --scope user glasser https://api.glasser.ai/mcp
    ```

    The user scope makes Glasser available across your local projects.
  </Step>

  <Step title="Sign in">
    Start Claude Code and enter `/mcp`. Select `glasser`, then **Authenticate**.

    In the browser, sign in to Glasser, choose your Workspace, and select **Allow**.
    Create an account and Workspace if needed. Return to Claude Code and check that Glasser
    is connected in `/mcp`.
  </Step>

  <Step title="Check the connection">
    In a new conversation, ask:

    ```text wrap theme={null}
    Use Glasser to check my available balance. Do not make any paid Runs.
    ```

    The agent should use Glasser's `balance` tool and return your balance. This check is free;
    a zero balance still means the connection works. If you need funds for a paid Run, add
    them in the [Glasser console](https://app.glasser.ai).
  </Step>
</Steps>

## Try your first request

```text wrap theme={null}
Use Glasser to find recent news about Stripe. Show me the data you can retrieve and the price, then wait for my approval before any paid Run.
```

After you approve, the agent can retrieve the data and report the result and charge.

See the [Claude Code MCP documentation](https://code.claude.com/docs/en/mcp) for server
configuration and authentication help.


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