How to Use the DevCycle MCP in AutoGen

Q: How do I register DevCycle tools in AutoGen?

Use mcpservertools with a StreamableHttpServerParams configuration. Pass the resulting tool list into your AssistantAgent constructor.

Give AutoGen multi-agent systems the ability to debate, verify, and execute DevCycle feature flag rollouts.

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 AutoGen

Create your Vinkius account to connect DevCycle 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 DevCycle with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent MCP Server Access

This MCP Server equips your AutoGen agents to negotiate feature releases directly through the API. A QA agent runs `list_project_environments` to verify staging setups. Meanwhile, a release manager agent calls `list_feature_flags` to check current deployment statuses. They deliberate before taking action. If the performance agent detects an issue, it demands a rollback. The release agent then executes `update_feature_flag_status` to disable the feature. You get consensus-driven state management without manual intervention.

Automated Targeting Verification

One agent executes `search_feature_flags` to locate a specific toggle before verifying the rollout. Another agent follows up with `get_feature_flag_details` to analyze the targeting rules and ensure the right user segments are exposed. The agents debate the configuration. If a security agent spots a missing constraint, it blocks the release. They only proceed when all conditions match your architectural guidelines.

Environment and Key Management

An operations agent runs `get_project_details` to confirm project scope and manage exact credentials. It then calls `get_environment_sdk_keys` to distribute the correct keys to testing frameworks. This eliminates manual credential shuffling. Your AutoGen system audits active setups by calling `list_active_flags` and `list_feature_variables`. The agents cross-check the data and alert you if staging keys are accidentally used in production.

Setup guide

Set up DevCycle 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 DevCycle 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="DevCycle_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent DevCycle 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="DevCycle_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent DevCycle 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 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 AutoGen

Use mcp_server_tools with a StreamableHttpServerParams configuration. Pass the resulting tool list into your AssistantAgent constructor.

Yes. You assign the DevCycle MCP tools to specific agents based on their roles. A reader agent might only access list_active_flags, while an executor agent handles status updates.

The agents read the error output from the tool and adjust their strategy. If get_feature_flag_details fails due to a bad ID, the agent automatically retries with a new search.

No. The McpToolAdapter handles all schema conversions automatically. Your agents instantly understand how to format requests for list_devcycle_projects.

Agents analyze infrastructure metadata, including project IDs and environment configurations. They read targeting logic but never ingest live application traffic or user identities. Vinkius manages the connection through a strict V8 Isolate Sandbox, keeping your core tokens completely insulated from the host machine.

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