How to Use the Codefresh MCP in AutoGen

Q: How do I register Codefresh tools with AutoGen agents?

Use the mcpservertools helper to fetch the tools from the server. You then pass this tool list directly into your AssistantAgent constructor so your agents can call them.

Q: How are Codefresh user profiles and account tokens secured in AutoGen?

Your account tokens and user profile data retrieved by getmycodefreshprofile are handled strictly within the secure V8 sandbox. No credential data is ever written to disk or shared with external LLM providers.

Let AutoGen agents debate and coordinate Codefresh build triggers and cluster deployments.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Codefresh MCP to AutoGen

Create your Vinkius account to connect Codefresh 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 Codefresh with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate Codefresh deployment risks

Set up a multi-agent workflow where a developer agent wants to run a build and a security agent reviews the risks. The developer agent calls `trigger_codefresh_build` only after both agents reach consensus on the safety of the target branch. The security agent can query `list_shared_contexts` to inspect environment variables before signing off. This collaborative check keeps your production environments safe from accidental or unapproved deployments.

Coordinate build monitoring using this MCP Server

Assign one agent to trigger the build and another to monitor its progress. The monitoring agent repeatedly calls `get_build_execution_details` to track the steps and reports back to the group. If the build fails, a debugging agent joins the conversation, analyzes the failure logs, and suggests fixes. This team-like coordination solves deployment issues without requiring your manual intervention.

Audit delivery clusters through multi-agent consensus

Run audits on your Kubernetes setups by letting agents cross-reference data. One agent gets the cluster list using `list_delivery_clusters` while another checks the active pipelines via `list_codefresh_pipelines`. They compare notes to find inactive clusters or orphaned pipelines. The agents debate which resources are safe to clean up and present you with a single, agreed-upon recommendation.

Setup guide

Set up Codefresh 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 Codefresh 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="Codefresh_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent Codefresh 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 Codefresh. 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 Codefresh 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 Codefresh MCP in AutoGen

Use the mcp_server_tools helper to fetch the tools from the server. You then pass this tool list directly into your AssistantAgent constructor so your agents can call them.

Yes, you can set up a user proxy and multiple assistant agents. One agent pulls the logs using get_build_execution_details while another analyzes the errors to find the root cause.

The agents can coordinate via group chats to sequence builds. They use list_codefresh_builds to check queue status before deciding to trigger a new workflow.

Yes, the MCP adapter supports both stdio and Streamable HTTP transports. This makes it easy to run the server locally or host it on a managed platform.

Your account tokens and user profile data retrieved by get_my_codefresh_profile are handled strictly within the secure V8 sandbox. No credential data is ever written to disk or shared with external LLM providers.

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