How to Use the CircleCI MCP in Vercel AI SDK

Q: How do I connect the CircleCI MCP Server to my Vercel AI SDK app?

Install the @ai-sdk/mcp package and define your connection. Use createMCPClient with the Vinkius HTTP transport URL. Pass the resulting tools into your streamText call.

Q: Can I trigger a CircleCI pipeline using the Vercel AI SDK?

Yes, the agent can call triggerccipipeline based on user input. You should implement a custom UI component to require manual confirmation before execution. That prevents accidental production deployments.

Q: Do I need to close the MCP client connection?

Always call mcpClient.close() when your route handler finishes. Leaving connections open will drain your Vinkius endpoint limits and cause memory leaks in your Edge functions.

Build React apps that manage CircleCI pipelines live. Vercel AI SDK streams job status and build details straight to your users.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CircleCI MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream CircleCI data to your frontend

Connect this MCP Server to your Vercel AI SDK application and watch build data appear instantly. Instead of showing users a spinning wheel while fetching CI status, your interface populates in real-time. Tools like `list_cci_pipelines` and `list_pipeline_workflows` feed directly into your React components as the LLM generates its response. Build dashboards that actually feel fast. When a user asks about a failed deployment, the agent calls `get_workflow_details` and streams the exact failure point back to the client. Edge function compatibility means these checks happen close to the user without dragging down your main server.

Let users launch jobs via Vercel AI SDK

Give your end users the ability to kick off deployments without leaving your app. By mapping the `trigger_cci_pipeline` tool to a chat interface, developers can type a quick message to start a build. The agent parses the request, confirms the target branch, and fires the command. You keep full control over the execution. Because the Vercel AI SDK handles the tool calling loop, you can render custom confirmation dialogues before the actual trigger happens. Once approved, the agent pulls the new status using `get_job_details` so the user knows the process started.

Expose CI environments safely

Finding out why a build failed usually means digging through logs. Now your AI client can do that heavy lifting in the background. The `list_workflow_jobs` tool grabs the specific tasks that ran, breaking down complex pipelines into readable chunks. Security remains tight because Vinkius handles the underlying token exchange. You just pass the HTTP endpoint URL into `createMCPClient()` and let the SDK manage the connection. Developers can check their permissions instantly using `get_my_cci_profile` right from the chat window.

Setup guide

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

Install the `@ai-sdk/mcp` package and define your connection. Use `createMCPClient` with the Vinkius HTTP transport URL. Pass the resulting tools into your `streamText` call.

Yes, the agent can call `trigger_cci_pipeline` based on user input. You should implement a custom UI component to require manual confirmation before execution. That prevents accidental production deployments.

Streaming eliminates perceived latency. When checking complex build paths with `list_pipeline_workflows`, the user sees the data flow into the UI immediately instead of waiting for a massive JSON payload to resolve.

Always call `mcpClient.close()` when your route handler finishes. Leaving connections open will drain your Vinkius endpoint limits and cause memory leaks in your Edge functions.

Vinkius runs the integration inside an ephemeral V8 Isolate sandbox. Your build logs, pipeline contexts, and workflow details exist only during the request lifecycle. Nothing gets stored or logged after the connection closes.

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