> For the complete documentation index, see [llms.txt](https://docs.ui-color-palette.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ui-color-palette.com/claude/configuration.md).

# Configuration

## User config

The plugin prompts for these values on first enable. You can update them at any time with `/plugin config`.

| Key              | Type     | Sensitive                | Required | Description                                                                                               |
| ---------------- | -------- | ------------------------ | -------- | --------------------------------------------------------------------------------------------------------- |
| `penpot_url`     | `string` | No                       | No       | Your Penpot instance base URL. Penpot Cloud: `https://design.penpot.app`. Self-hosted: your own domain    |
| `penpot_token`   | `string` | Yes — stored in keychain | No       | Your Penpot user token. Find it in Penpot → Account → Integrations → MCP Server                           |
| `framer_mcp_url` | `string` | No                       | No       | Your Framer MCP URL from the [Framer marketplace plugin](https://www.framer.com/marketplace/plugins/mcp/) |
| `gitlab_url`     | `string` | No                       | No       | Your GitLab instance URL (e.g. `https://gitlab.company.com`) — leave empty if not using GitLab            |

Sensitive values are stored in the system keychain and never written to `settings.json`.

## MCP servers

The plugin connects to the following MCP servers automatically when enabled:

| Server               | Transport | URL                                        | Auth                                            |
| -------------------- | --------- | ------------------------------------------ | ----------------------------------------------- |
| **UI Color Palette** | HTTP      | `https://mcp-uicp.yelbolt.workers.dev/mcp` | OAuth 2.0 (optional)                            |
| **Figma**            | HTTP      | `https://mcp.figma.com/mcp`                | OAuth                                           |
| **Figma Desktop**    | HTTP      | `http://127.0.0.1:3845/mcp`                | Local                                           |
| **Penpot**           | HTTP      | `${penpot_url}/mcp/stream?userToken=…`     | URL via `penpot_url` · token via `penpot_token` |
| **Sketch**           | HTTP      | `http://localhost:31126/mcp`               | Local                                           |
| **Framer**           | HTTP      | URL via `framer_mcp_url`                   | Token in URL                                    |
| **GitHub**           | HTTP      | `https://api.githubcopilot.com/mcp/`       | OAuth                                           |
| **GitLab**           | HTTP      | `${gitlab_url}/api/v4/mcp`                 | OAuth                                           |

## Default agent

The plugin sets `uicper` as the default agent in `settings.json`:

```json
{
  "agent": "uicper"
}
```

This means multi-step requests that don't specify a skill are handled by the orchestrator. See [Agents](/claude/agents.md) for details.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.ui-color-palette.com/claude/configuration.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.