# CodePanel in Claude

URL: https://codepanel.ai/agents/claude-apps

Claude reads CodePanel reviews and rates findings in chat through a remote MCP server, while a coding agent pushes the fixes.

Claude runs on the web, Claude Desktop and the mobile apps. With CodePanel it is where a person asks about a review in plain language: what the panel found on a pull request, why a finding was raised, or to rate one as fixed. Through the connector it reads and rates; the fixes come from a coding agent, such as [Claude Code](/agents/claude-code).

## How Claude connects

Claude connects through a remote MCP server at `https://codepanel.ai/mcp`. The steps are in [Claude and ChatGPT apps](/docs/claude-and-chatgpt).

## Claude features for the review loop

| Feature | What the docs say | Source |
| --- | --- | --- |
| Maker | Anthropic | [support.claude.com](https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp) |
| Runs in | the web, Claude Desktop and the mobile apps | [claude.com](https://claude.com/docs/connectors/getting-started) |
| MCP | Remote servers over Streamable HTTP as custom connectors, with OAuth, reached from Anthropic's cloud | [support.claude.com](https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp), [page 2](https://claude.com/docs/connectors/building/index), [page 3](https://claude.com/docs/connectors/custom/add-unlisted) |
| Models | Claude models: Haiku, Sonnet, Opus and Fable. Prices: [Anthropic](/models/anthropic). | [support.claude.com](https://support.claude.com/en/articles/8664678-change-the-model-effort-and-thinking-settings) |

Each row was checked on 2026-10-17 against the maker's docs it cites. A feature with no row is one those docs don't describe.