2,500+ MCP servers ready to use
Vinkius

CodeRabbit MCP Server for Vercel AI SDK 9 tools — connect in under 2 minutes

Built by Vinkius GDPR 9 Tools SDK

The Vercel AI SDK is the TypeScript toolkit for building AI-powered applications. Connect CodeRabbit through Vinkius and every tool is available as a typed function. ready for React Server Components, API routes, or any Node.js backend.

Vinkius supports streamable HTTP and SSE.

typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

async function main() {
  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      // Your Vinkius token. get it at cloud.vinkius.com
      url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    },
  });

  try {
    const tools = await mcpClient.tools();
    const { text } = await generateText({
      model: openai("gpt-4o"),
      tools,
      prompt: "Using CodeRabbit, list all available capabilities.",
    });
    console.log(text);
  } finally {
    await mcpClient.close();
  }
}

main();
CodeRabbit
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About CodeRabbit MCP Server

Connect your CodeRabbit organization to any AI agent and take full control of your AI-powered code review operations through natural conversation.

The Vercel AI SDK gives every CodeRabbit tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 9 tools through Vinkius and stream results progressively to React, Svelte, or Vue components. works on Edge Functions, Cloudflare Workers, and any Node.js runtime.

What you can do

  • User Management — List all organization members, filter by seat assignment or role, and inspect individual profiles
  • Seat Control — Bulk assign or unassign CodeRabbit seats to enable or disable AI code reviews for team members
  • Role Administration — Promote members to admin or demote admins to member role in bulk operations
  • PR Review Metrics — Retrieve complexity scores, review times, and comment breakdowns for merged pull requests across any date range
  • Compliance Audit Logs — Access tamper-resistant records of administrative actions for SIEM integration and compliance reporting
  • Configuration — View and update seat assignment modes (automatic vs. manual)

The CodeRabbit MCP Server exposes 9 tools through the Vinkius. Connect it to Vercel AI SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect CodeRabbit to Vercel AI SDK via MCP

Follow these steps to integrate the CodeRabbit MCP Server with Vercel AI SDK.

01

Install dependencies

Run npm install @ai-sdk/mcp ai @ai-sdk/openai

02

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

03

Run the script

Save to agent.ts and run with npx tsx agent.ts

04

Explore tools

The SDK discovers 9 tools from CodeRabbit and passes them to the LLM

Why Use Vercel AI SDK with the CodeRabbit MCP Server

Vercel AI SDK provides unique advantages when paired with CodeRabbit through the Model Context Protocol.

01

TypeScript-first: every MCP tool gets full type inference, IDE autocomplete, and compile-time error checking out of the box

02

Framework-agnostic core works with Next.js, Nuxt, SvelteKit, or any Node.js runtime. same CodeRabbit integration everywhere

03

Built-in streaming UI primitives let you display CodeRabbit tool results progressively in React, Svelte, or Vue components

04

Edge-compatible: the AI SDK runs on Vercel Edge Functions, Cloudflare Workers, and other edge runtimes for minimal latency

CodeRabbit + Vercel AI SDK Use Cases

Practical scenarios where Vercel AI SDK combined with the CodeRabbit MCP Server delivers measurable value.

01

AI-powered web apps: build dashboards that query CodeRabbit in real-time and stream results to the UI with zero loading states

02

API backends: create serverless endpoints that orchestrate CodeRabbit tools and return structured JSON responses to any frontend

03

Chatbots with tool use: embed CodeRabbit capabilities into conversational interfaces with streaming responses and tool call visibility

04

Internal tools: build admin panels where team members interact with CodeRabbit through natural language queries

CodeRabbit MCP Tools for Vercel AI SDK (9)

These 9 tools become available when you connect CodeRabbit to Vercel AI SDK via MCP:

01

assign_seats

Up to 500 user IDs per request. Assign CodeRabbit seats to users

02

demote_users

Demote users from admin to member role

03

get_audit_logs

Ideal for compliance reporting. Retrieve organization audit logs

04

get_metrics

Useful for engineering productivity analysis. Retrieve PR review metrics for a date range

05

get_seat_mode

Get the current seat assignment mode

06

list_users

Optionally filter by seat assignment status or role. List all users in the CodeRabbit organization

07

promote_users

Promote users to admin role

08

unassign_seats

Does not delete user accounts. Remove CodeRabbit seats from users

09

update_seat_mode

Requires Enterprise plan. Update the seat assignment mode

Example Prompts for CodeRabbit in Vercel AI SDK

Ready-to-use prompts you can give your Vercel AI SDK agent to start working with CodeRabbit immediately.

01

"Show me all team members who don't have a CodeRabbit seat assigned."

02

"What were our code review metrics for March 2026?"

03

"Show me the audit trail of admin actions from last week."

Troubleshooting CodeRabbit MCP Server with Vercel AI SDK

Common issues when connecting CodeRabbit to Vercel AI SDK through the Vinkius, and how to resolve them.

01

createMCPClient is not a function

Install: npm install @ai-sdk/mcp

CodeRabbit + Vercel AI SDK FAQ

Common questions about integrating CodeRabbit MCP Server with Vercel AI SDK.

01

How does the Vercel AI SDK connect to MCP servers?

Import createMCPClient from @ai-sdk/mcp and pass the server URL. The SDK discovers all tools and provides typed TypeScript interfaces for each one.
02

Can I use MCP tools in Edge Functions?

Yes. The AI SDK is fully edge-compatible. MCP connections work on Vercel Edge Functions, Cloudflare Workers, and similar runtimes.
03

Does it support streaming tool results?

Yes. The SDK provides streaming primitives like useChat and streamText that handle tool calls and display results progressively in the UI.

Connect CodeRabbit to Vercel AI SDK

Get your token, paste the configuration, and start using 9 tools in under 2 minutes. No API key management needed.