Code review with Cursor
Cursor, Anysphere's coding agent, in CodePanel's review loop: it connects through MCP and skills, reads Cursor rules and answers every finding.
Cursor is Anysphere's coding agent, in its own editor, a CLI, JetBrains IDEs through the Agent Client Protocol, cloud agents and an iOS app. With CodePanel it is the author on the other side of the review: after it pushes, it reads the panel's findings on that commit over MCP, fixes or disputes each one with evidence, and rates every finding. It reads .cursor/rules/*.mdc, AGENTS.md and CLAUDE.md, and the setup skill writes the loop into AGENTS.md or CLAUDE.md.
How Cursor connects
Cursor connects through an MCP server entry in ~/.cursor/mcp.json and the codepanel and codepanel-setup skills. The steps are in Cursor.
Cursor features for the review loop
| Feature | What the docs say | Source |
|---|---|---|
| Maker | Anysphere | cursor.com |
| Runs in | its own editor, a CLI, JetBrains IDEs through the Agent Client Protocol, cloud agents and an iOS app | cursor.com, page 2, page 3, page 4, page 5 |
| MCP | stdio, SSE and Streamable HTTP servers, with OAuth, in .cursor/mcp.json or ~/.cursor/mcp.json |
cursor.com |
| Hooks | Scripts that speak JSON over stdio, set in hooks.json; stop handles the agent finishing |
cursor.com |
| GitHub Actions | A documented workflow that installs the CLI and runs agent -p with CURSOR_API_KEY |
cursor.com |
| Headless mode | agent -p "<prompt>", with --force to apply edits |
cursor.com |
| Rules files | .cursor/rules/*.mdc, AGENTS.md, CLAUDE.md |
cursor.com, page 2 |
| Models | Cursor's own models and models from OpenAI, Anthropic, Google and others, or your own key for OpenAI, Anthropic, Google, Azure OpenAI and AWS Bedrock. Prices: OpenAI, Anthropic, Google, xAI, Moonshot, Z.ai. | cursor.com, page 2 |
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.
Read next
AGENTS.md for an agent-to-agent review loop
What to put in AGENTS.md so a coding agent answers AI code review on its own: how each agent loads the file, the review section, and one file for every agent.
CLAUDE.md for an agent-to-agent review loop
What to put in CLAUDE.md so Claude Code sees AI code review through to merge: what loads when, where the loop goes, the size target, and sharing with AGENTS.md.
Cursor rules for an agent-to-agent review loop
Cursor rules for AI code review: which .mdc rule type to use, scoping a rule with globs like a .codepanel/rules.md section, and when to use AGENTS.md.