How to Use the Codacy MCP in Vercel AI SDK

Stream live Codacy repository quality grades directly to your React components using the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Codacy MCP to Vercel AI SDK

Create your Vinkius account to connect Codacy to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Codacy with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time code quality metrics in your AI SDK UI

Your Next.js app can now display active repository grades without making your users stare at a blank loading screen. This MCP server lets your Vercel AI SDK client pull raw metrics using `get_repository_quality_analysis` and feed them directly into streamText for instant UI updates. Instead of waiting for a slow backend fetch, the agent gets the grade, issues, and language breakdown right away. Your users watch the code analysis populate the screen component by component as the LLM processes the payload.

Interactive issue search built for your AI SDK chat

Let users hunt down technical debt directly inside your chat interface. By passing `search_repository_issues` to your Vercel AI SDK tool configuration, your agent can pinpoint specific security flaws or style violations on the fly. The tool output feeds straight into your React components, letting you render interactive lists of code issues. It keeps developers in their flow without forcing them to open the main Codacy dashboard in another browser tab.

Live organization auditing via the Vercel AI SDK

Map out entire codebases and team structures inside your custom developer portal. Your application calls `list_codacy_organizations` and `list_organization_repositories` to let the agent map out which projects need attention. Because this MCP Server works with edge functions, you get instant responses without cold-start delays. You can build lightweight dashboards that show exactly who has access and which repositories are slipping in quality.

Setup guide

Set up Codacy MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Codacy tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Codacy transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Codacy. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Codacy now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Codacy MCP in Vercel AI SDK

You initialize the client and pass the tools directly to streamText. The agent calls `get_repository_quality_analysis` and streams the JSON response to your frontend in real-time.

Yes, the server runs in a V8 sandbox and connects over standard HTTP. You just set up the Vercel AI SDK client using createMCPClient and call mcpClient.close once the streaming completes.

You configure the authProvider during the createMCPClient setup. This lets your React frontend securely pass the user's token so they can run `get_my_codacy_profile` safely.

Always call mcpClient.close at the end of your route handler. This prevents hanging HTTP connections and ensures your serverless functions spin down properly after fetching repository data.

It only touches repository metadata, quality grades, and static analysis issues. Your raw source code is never read or stored, and all connections run through Vinkius's isolated, zero-trust sandbox.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript