How to Use the DeepSource MCP in Vercel AI SDK

Q: How does Vercel AI SDK display live DeepSource analysis runs?

Use listanalysisruns inside your streaming text tool definition. The SDK pipes the analyzer status directly into the UI stream as the runs complete.

Q: How do I update repository branches using Vercel AI SDK?

Call updatedefaultbranch with the repository ID from your client. The agent handles the change and updates your internal UI dashboard to reflect the new target branch.

Stream DeepSource repository health grades and vulnerability alerts directly into your Next.js UI using 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 DeepSource MCP to Vercel AI SDK

Create your Vinkius account to connect DeepSource 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 DeepSource with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live repository grades to your frontends

The `get_report_card` tool pulls the current letter grade and code health trends directly from your VCS provider. Your Vercel AI SDK client renders this data instantly, so users see active code quality metrics without staring at a loading spinner. If the code grade drops, your interface updates dynamically. You can trigger `get_repository_metrics` to pinpoint the exact file causing the drop, showing cyclomatic complexity or maintainability index numbers right on the screen.

Resolve security issues on the fly

The `list_vulnerabilities` tool identifies security risks in your repository dependencies. When your security team opens the app, the agent uses it to fetch active dependency risks and CVSS scores. If they need more detail, the interface triggers `get_vulnerability` to pull the exact dependency path. Your user can read the vulnerability details and decide on patch actions right inside your custom dashboard without logging into another tool.

Control analysis runs via Vercel AI SDK

The `activate_repository` tool turns on analysis runs for any new repository. This MCP Server lets your application configure DeepSource tracking programmatically so you don't have to jump into a separate dashboard to onboard a project. You can also use `deactivate_repository` to pause tracking on archived codebases. If a key token is leaked, calling `regenerate_dsn` rotates the credentials immediately, keeping your integration secure and up to date.

Setup guide

Set up DeepSource 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 DeepSource 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 DeepSource 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 DeepSource. 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 DeepSource 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 DeepSource MCP in Vercel AI SDK

Pass your token through the authProvider configuration when setting up the client. Use `get_viewer` to verify the token is valid before letting the user run any analysis queries.

Yes. The MCP integration is fully compatible with Edge runtimes. You call `get_test_coverage` or `get_repository_metrics` inside your route handler and stream the JSON chunks straight to your React components.

Use `list_analysis_runs` inside your streaming text tool definition. The SDK pipes the analyzer status directly into the UI stream as the runs complete.

Call `update_default_branch` with the repository ID from your client. The agent handles the change and updates your internal UI dashboard to reflect the new target branch.

This server only accesses code analysis metrics, repository metadata, and vulnerability scan results. Your actual source code never leaves your VCS provider or DeepSource, ensuring your proprietary code remains private.

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