How to Use the DevCycle MCP in Vercel AI SDK

Q: How do I search for feature flags in DevCycle using Vercel AI SDK?

You use the searchfeatureflags tool within your agent logic. Pass your keyword to the tool, and it returns matching flags from your project immediately.

Q: Can Vercel AI SDK update flag statuses via the DevCycle MCP Server?

Yes, but you should restrict access. Use updatefeatureflagstatus cautiously, preferably with a human-in-the-loop requirement for production changes.

Stream feature flag data directly into your Vercel AI SDK interface for real-time visibility.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DevCycle MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live flag monitoring in Vercel AI SDK

Hook your AI client into the DevCycle API to pull current flag states. Instead of static logs, use `list_active_flags` to render the actual state of your application features directly in your front-end components. Your users see the AI identify and toggle features as they happen. Calling `get_feature_flag_details` gives the agent the context it needs to explain why a feature is active or disabled in the UI.

Manage environments from your interface

Stop switching tabs to check which SDK keys are active. This MCP Server exposes `list_project_environments` and `get_environment_sdk_keys` so your agent can verify configuration settings without leaving your development flow. Everything happens inside the stream. Your AI client can query `list_devcycle_projects` to confirm it is looking at the correct workspace before attempting any configuration changes.

Automated variable tracking

Let your agent handle the tedious task of auditing feature variables. By executing `list_feature_variables`, your AI client can compare code-level definitions against what is currently deployed in your project. This keeps your codebase clean by identifying stale variables that no longer serve a purpose. It is a faster way to maintain consistency across your Vercel AI SDK deployments.

Setup guide

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

You use the `search_feature_flags` tool within your agent logic. Pass your keyword to the tool, and it returns matching flags from your project immediately.

Yes, but you should restrict access. Use `update_feature_flag_status` cautiously, preferably with a human-in-the-loop requirement for production changes.

It does. The tool output flows directly into your stream text generation, letting the AI provide updates as it retrieves them.

The server is ephemeral and does not persist your data. It acts as a pass-through for API keys and flag configurations during your active session.

Your SDK keys and project identifiers are processed only during the tool execution. We do not log your feature flag configurations or environment secrets.

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