How to Use the DevCycle MCP in OpenAI Agents SDK

Q: How do I connect DevCycle to the OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance using your Vinkius endpoint URL. Pass it into your Agent constructor within the mcpservers list, and set cacheToolsList=True to speed up initialization.

Q: Can the OpenAI Agents SDK automatically toggle DevCycle flags?

Yes, but you control the boundaries. The agent can call updatefeatureflagstatus to turn features on or off. You should configure SDK guardrails to require human approval for production environments while allowing autonomous toggles in staging.

Give your OpenAI Agents SDK production-grade control over DevCycle feature flags with built-in execution guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect DevCycle to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Rollouts with OpenAI Agents SDK

You don't want an agent toggling production flags blindly. By connecting this MCP Server, your agent reads state via `list_active_flags` and proposes changes. The SDK's built-in guardrails catch the execution before `update_feature_flag_status` fires, letting you approve the exact targeting rules first. Handoffs work perfectly here. You build a read-only agent that monitors `list_project_environments` and `get_feature_flag_details`. When it spots a stale flag, it passes context to an execution agent. That second agent requests the deletion, keeping your blast radius strictly contained.

Audit Every State Change

Tracing matters when flags break things. Because the agent uses `get_environment_sdk_keys` and `list_feature_variables` through standard tools, the OpenAI dashboard logs every payload. You see exactly what context the agent pulled before making a decision. The agent doesn't guess project IDs. It runs `list_devcycle_projects` first. If it needs to find a specific release toggle, it triggers `search_feature_flags` with your keyword. You get a complete paper trail of how it mapped a natural language request to a specific variable.

Map Project Environments Fast

Getting an agent to understand your deployment tiers usually takes massive prompt engineering. Here, it just calls `get_project_details`. The MCP protocol hands back the exact schema DevCycle expects, grounding the agent in reality. If a developer asks the agent why a feature is hidden in staging, it checks `list_feature_flags`. It correlates the current statuses across environments and tells you exactly which rule is failing. No portal logins required.

Setup guide

Set up DevCycle MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all DevCycle tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives DevCycle tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate DevCycle tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="DevCycle Agent",
            instructions="You have access to DevCycle tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance using your Vinkius endpoint URL. Pass it into your `Agent` constructor within the `mcp_servers` list, and set `cacheToolsList=True` to speed up initialization.

Yes, but you control the boundaries. The agent can call `update_feature_flag_status` to turn features on or off. You should configure SDK guardrails to require human approval for production environments while allowing autonomous toggles in staging.

The API rejects the call. The agent will typically catch the error and run `list_devcycle_projects` to find the correct ID. It self-corrects based on the live data.

The MCP Server processes requests as they come in. If you hit DevCycle's limits during heavy polling of `list_feature_flags`, the SDK's retry logic handles the backoff automatically.

Vinkius isolates this connection in an ephemeral V8 sandbox. The server reads your feature flag rules and SDK keys, passes them directly to your agent, and shuts down. Zero persistent storage means your release schedules stay 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