How to Use the Codefresh MCP in Mastra AI

Automate complex GitOps workflows in Mastra AI with conditional branching and automatic retries.

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 Mastra AI

Create your Vinkius account to connect Codefresh to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate deployments with Mastra AI

Chain `list_codefresh_pipelines` and `trigger_codefresh_build` into your agent workflows. If a pipeline fails, Mastra AI can detect the state and trigger a retry or notify your team. This setup turns static CI/CD tasks into dynamic, self-healing processes. You define the branches, and the agent handles the logic.

Manage shared contexts automatically

Pull your environment variables and secrets using `list_shared_contexts` to inform your agent decisions. This makes sure your automation has the right credentials before it starts a task. Your workflows stay clean because the agent pulls the necessary context on demand. It keeps your secrets managed in one place.

Query build execution details

Call `get_build_execution_details` to get a deep dive into why a build stalled. Your agent can then summarize the issues for your developers. It saves you from digging through raw logs. The agent gives you the summary you need to fix the problem fast.

Setup guide

Set up Codefresh MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Codefresh tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "codefresh-mcp-client",
  servers: {
    "codefresh-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Codefresh Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Codefresh tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Codefresh transactions"
);
console.log(result.text);

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 Mastra AI

Add the server to your agent configuration and list the tools. Your agent will then see the Codefresh capabilities as available functions for its logic tree.

Use the tool approval setting to pause execution. A human must confirm before the agent triggers a build or changes a pipeline state.

You absolutely can. Just link the trigger tool to your agent's task list to automate your release cycle.

The framework supports automatic retries with backoff. You can configure the agent to attempt a task again if the initial connection to the server drops.

Your account tokens and environment variables are stored in a secure vault. Access is restricted to the specific agent tasks you authorize.

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