How to Use the Codefresh MCP in Google ADK

Q: Can Google ADK limit which Codefresh actions an agent can perform?

Yes, you can use the toolnames filter in the ADK setup to restrict access. For example, you can allow listcodefreshbuilds while blocking triggercodefreshbuild entirely.

Q: Is my Codefresh cluster data safe when using Google ADK?

Absolutely. Your Kubernetes cluster lists retrieved via listdeliveryclusters are processed locally within your GCP environment and Vinkius's zero-trust runtime, ensuring zero external exposure of your internal network topology.

Run enterprise GitOps by connecting Codefresh to your Google ADK pipelines with this dedicated MCP Server.

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 Google ADK

Create your Vinkius account to connect Codefresh to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Codefresh GitOps Data in Google ADK

Feed your massive deployment history straight into Gemini's long-context window. Your agent uses `list_codefresh_builds` to pull months of execution logs and pinpoint why certain pipelines consistently fail. By combining this telemetry with Google ADK, you can write agents that cross-reference build errors with your infrastructure logs in BigQuery.

Automated Cluster Audits with this MCP Server

Keep your Kubernetes environments clean without manual checks. The agent runs `list_delivery_clusters` to catalog every active target and compares it against your GCP project settings. If it spots an orphaned cluster, it flags it immediately. It can also query `list_shared_contexts` to verify that your secrets match the target environment.

Intelligent Pipeline Triggering and Monitoring

Let your agent manage the release cycle based on real-time code changes. It calls `trigger_codefresh_build` to start the workflow, then tracks its status using `get_build_execution_details`. The MCP integration reads the YAML structure via `get_pipeline_configuration` to understand the layout and suggest the exact fix if a step fails.

Setup guide

Set up Codefresh MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Codefresh tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Codefresh_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Codefresh tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You initialize the McpToolset with the Vinkius HTTP URL and pass it to your LlmAgent. Your Gemini-powered agent instantly gains access to tools like `list_codefresh_pipelines`.

Yes, you can use the `tool_names` filter in the ADK setup to restrict access. For example, you can allow `list_codefresh_builds` while blocking `trigger_codefresh_build` entirely.

Gemini's large context window lets the agent ingest complete pipeline definitions from `get_pipeline_configuration`. It can analyze thousands of lines of build configurations to find optimizations.

You can write a Google ADK agent that monitors BigQuery datasets and calls `trigger_codefresh_build` when new data triggers are met.

Absolutely. Your Kubernetes cluster lists retrieved via `list_delivery_clusters` are processed locally within your GCP environment and Vinkius's zero-trust runtime, ensuring zero external exposure of your internal network topology.

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