How to Use the Flagsmith MCP in AutoGen

Q: How do AutoGen agents collaborate to update a Flagsmith flag?

One agent proposes a change using updateflagv1, while a validator agent checks the environment state via getenvironmentflags. They only commit the change once both agree.

Q: Can AutoGen handle user traits in Flagsmith?

Yes, agents use identifyuser to set traits and getidentityflags to evaluate them. This lets different agents simulate various user profiles to test targeting rules.

Q: How do I secure Flagsmith API keys in an AutoGen setup?

The FLAGSMITHAPIKEY is restricted to the Vinkius execution environment. AutoGen agents can only interact with it through predefined tools like updateflagv2, keeping keys hidden from the LLM prompt space.

Q: Can agents delete segment overrides?

Yes. An agent can call deletesegmentoverride to remove a specific override once a testing scenario is complete.

Let AutoGen agents debate and coordinate Flagsmith feature rollouts based on real-time system metrics.

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 AutoGen

Create your Vinkius account to connect Flagsmith to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate feature rollouts using the Flagsmith MCP Server

The `update_flag_v2` tool allows your release agent to batch-update flags once the QA agent approves. This MCP integration lets agents discuss the performance impact before committing changes to the environment. If the security agent flags a risk, it can trigger `delete_segment_override` to roll back the changes. This multi-agent consensus prevents accidental deployments.

Coordinate user segmentation across agent roles

Use `identify_user` to set traits for a customer segment during a simulated user scenario. One agent acts as the customer while another monitors how the flags respond to those traits. The monitoring agent calls `get_identity_flags` to verify that the user received the correct experience. This automates complex QA testing of your segmentation rules.

Verify environment configurations before rollout

The `get_environment_document` tool retrieves the complete environment configuration for the team of agents to inspect. The agents analyze the JSON structure to find conflicting rules. After reaching a consensus on the optimal setup, they use `create_environment` to apply the verified configuration to a fresh staging environment.

Setup guide

Set up Flagsmith MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Flagsmith tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Flagsmith_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Flagsmith data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Flagsmith_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Flagsmith data")
    print(result.messages[-1].content)

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 AutoGen

One agent proposes a change using `update_flag_v1`, while a validator agent checks the environment state via `get_environment_flags`. They only commit the change once both agree.

Yes, agents use `identify_user` to set traits and `get_identity_flags` to evaluate them. This lets different agents simulate various user profiles to test targeting rules.

The FLAGSMITH_API_KEY is restricted to the Vinkius execution environment. AutoGen agents can only interact with it through predefined tools like `update_flag_v2`, keeping keys hidden from the LLM prompt space.

Yes. An agent can call `delete_segment_override` to remove a specific override once a testing scenario is complete.

This MCP server only sends user identities and traits to Flagsmith endpoints. Vinkius runs the server in an ephemeral sandbox, ensuring no customer data is logged or retained on the host system.

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