An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect CodeRabbit to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run your entire AI code review workflow through conversation.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 9 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-03

3 capabilities in this set.

Part of 9 available through CodeRabbit.

  1. 01

    List users

    This capability lists all users within your CodeRabbit organization. You can filter the results by specific roles or seat assignment status.

  2. 02

    Get audit logs

    This capability retrieves organization audit logs. It is designed for pulling records needed for compliance reporting.

  3. 03

    Get seat mode

    This capability checks your current seat assignment mode. Use it to see if your organization is set to automatic or manual assignment.

Capability set02 / 03

04-06

3 capabilities in this set.

Part of 9 available through CodeRabbit.

  1. 04

    Promote users

    This capability upgrades users to an admin role. Use it to quickly grant administrative permissions to team members.

  2. 05

    Unassign seats

    This capability removes CodeRabbit seats from specific users. It does not delete the user accounts themselves.

  3. 06

    Assign seats

    This capability assigns CodeRabbit seats to users. You can process up to 500 user IDs in a single request.

Capability set03 / 03

07-09

3 capabilities in this set.

Part of 9 available through CodeRabbit.

  1. 07

    Demote users

    This capability changes an admin's role back to a standard member. Use it to revoke administrative privileges.

  2. 08

    Get metrics

    This capability pulls PR review metrics for a specific date range. It provides data on review times and complexity scores.

  3. 09

    Update seat mode

    This capability changes how seats are assigned in your organization. This specific action requires an Enterprise plan.

Real work

What teams actually run

01

Onboarding New Engineers

Ask your agent to assign seats to a list of new team members immediately after they join.

02

Weekly Performance Reviews

Request a summary of PR review times and complexity scores to evaluate team throughput.

03

Security Audits

Pull a list of recent administrative changes to verify compliance with internal policies.

04

Permission Cleanup

Use the agent to demote users or unassign seats when team structures change.

Automate a task

Put CodeRabbit to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

CodeRabbit works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put CodeRabbit to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

925ms average. Fast in production.

CodeRabbit is checked daily against the live service.

Daily averagePeak 1055ms
Oct 3Today
Fastest day
730ms
Slowest day
1055ms
14-day trend
Slowing+10%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 9 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of CodeRabbit, so you can see the experience inside your AI.

It does not authenticate your account with CodeRabbit. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

CodeRabbit Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_PMcRlSWUfPE40MnPxowwrCoT2UjR21cc7zb3FshU/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — CodeRabbit capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "coderabbit-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_PMcRlSWUfPE40MnPxowwrCoT2UjR21cc7zb3FshU/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up CodeRabbit in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work CodeRabbit owners hand off.

This MCP is built for technical leaders who need to manage CodeRabbit without constantly logging into the web dashboard.

  • 01

    Engineering Managers

    They ask the agent for team velocity and code review quality metrics.

  • 02

    Platform Engineers

    They use the agent to automate seat and role management across large teams.

  • 03

    Compliance Officers

    They query the agent for audit logs to satisfy security reporting requirements.

FAQ

Questions CodeRabbit owners ask.

  • 01

    How do I connect this MCP to my AI client?

    You subscribe to the MCP on Vinkius and enter your CodeRabbit API key. Once connected, you can use it immediately in Claude, Cursor, or Windsurf.

  • 02

    Can I assign seats to many users at once?

    Yes. You can use the agent to assign seats to up to 500 user IDs in a single request.

  • 03

    Does unassigning a seat delete the user?

    No. Unassigning a seat only removes the CodeRabbit license from that user; it does not delete their account.

  • 04

    Is the audit log data secure?

    Yes. The audit logs are tamper-resistant and can be used for SIEM integration and compliance reporting.

  • 05

    Do I need an Enterprise plan to change seat modes?

    Yes. Updating the seat assignment mode requires an Enterprise plan.

  • 06

    Can I see how productive my team's code review process is over the last month?

    Yes! Use the get_metrics capability with a date range (e.g., 2026-03-01 to 2026-03-31). It returns complexity scores, average review times, and comment breakdowns categorized by severity for all merged PRs.

  • 07

    How do I enable AI code reviews for new team members?

    First run list_users with seat_filter=unassigned to find members without seats. Then use assign_seats with their user IDs to grant them AI-powered code review access instantly.

  • 08

    Can I audit who made administrative changes in the organization?

    Absolutely. The get_audit_logs capability returns a complete, tamper-resistant trail of all admin actions including seat assignments, role changes, configuration updates, and API key operations. You can filter by action type and date range.

Explore

More in AI Frontier

Suggestions

Connect CodeRabbit to Claude, Cursor, ChatGPT & more