How to Use the Flagsmith MCP in OpenAI Agents SDK

Q: How do I initialize the Flagsmith MCP Server using the openai-agents-sdk?

Install the package using pip install openai-agents first. Then, instantiate MCPServerStreamableHttp using MCPServerStreamableHttpParams with your Vinkius endpoint URL. Pass this server object inside the mcpservers list when initializing your Agent class.

Q: Why should I set cacheToolsList to true in this setup?

Setting cacheToolsList=True prevents the SDK from repeatedly querying the Vinkius endpoint for tool definitions. It speeds up agent initialization and ensures your agent is responsive when calling tools like getidentityflags.

Toggle Flagsmith features and configure environments safely using production-grade OpenAI Agents SDK guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flagsmith MCP to OpenAI Agents SDK

Create your Vinkius account to connect Flagsmith 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 Flagsmith with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control Flagsmith flag states with OpenAI Agents SDK

The `get_environment_flags` tool lets your agent fetch default flag states directly from Flagsmith to determine active features. This tool serves as the entry point for your agent to inspect what is currently live across your system before making routing decisions. Your Python agent uses these default states to dynamically branch execution paths. Because the agent auto-discovers this MCP Server, it can immediately read configurations without you writing custom boilerplate code to parse raw JSON payloads.

Update environment configurations in batches safely

The `update_flag_v2` tool allows your agent to execute multi-flag modifications over MCP in a single operation. This batch approach keeps your environment in sync during automated rollbacks or complex deployment steps. OpenAI's built-in guardrails validate these batch updates before they hit production. If an agent tries to push an invalid configuration, the SDK intercepts the payload, preventing broken states from reaching your users.

Target specific users using identity-based routing

The `identify_user` tool binds specific traits to an active user session so your agent can serve personalized flags. This tool lets your agent build a context-rich profile before evaluating which features are active. Once identified, the agent calls `get_identity_flags` to retrieve the exact flag states assigned to that user. The OpenAI dashboard traces this entire handoff, giving you a clear audit trail of why a specific flag was evaluated for a given user.

Setup guide

Set up Flagsmith 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 Flagsmith tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Flagsmith 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="Flagsmith Agent",
            instructions="You have access to Flagsmith 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 Flagsmith. 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 Flagsmith 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 Flagsmith MCP in OpenAI Agents SDK

Install the package using `pip install openai-agents` first. Then, instantiate `MCPServerStreamableHttp` using `MCPServerStreamableHttpParams` with your Vinkius endpoint URL. Pass this server object inside the `mcp_servers` list when initializing your `Agent` class.

Yes, you can set up a specialized agent for flag evaluation and another for configuration changes. The evaluation agent reads flags via `get_environment_flags`, then hands off to a writer agent to call `update_flag_v1` if a change is needed.

You configure the built-in guardrails in the SDK to intercept calls to `update_flag_v2` or `create_environment`. The runtime checks the proposed changes against your validation policies before letting the agent execute the tool.

Setting `cacheToolsList=True` prevents the SDK from repeatedly querying the Vinkius endpoint for tool definitions. It speeds up agent initialization and ensures your agent is responsive when calling tools like `get_identity_flags`.

This server handles Flagsmith API keys, environment configurations, and user trait data. Vinkius runs the MCP Server in an ephemeral, zero-trust V8 Isolate sandbox, ensuring your API credentials and user traits are never written to persistent disk or exposed to other tenants.

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