How to Use the Codefresh MCP in Windsurf

Q: How do I connect the Codefresh MCP Server to Windsurf?

Add the server to your /.codeium/windsurf/mcpconfig.json file under the mcpServers key. Cascade automatically detects the new tools upon restart, or you can click refresh in the Windsurf MCP panel.

Q: Can Windsurf Cascade trigger Codefresh builds autonomously?

Yes. Cascade chains tools like listcodefreshpipelines and triggercodefreshbuild to start runs when you save your work. It plans the sequence and runs the build without prompting you for every step.

Q: How does Windsurf display Codefresh pipeline failures?

Cascade calls getbuildexecutiondetails to fetch the raw error logs directly into your chat. It then highlights the exact lines of code in your open editor that caused the failure.

Trigger Codefresh builds and debug failing pipelines directly from your Windsurf Cascade chat.

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 Windsurf

Create your Vinkius account to connect Codefresh to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Build Debugging in Windsurf

Cascade uses `get_build_execution_details` and `list_codefresh_builds` to spot failing steps in your CI pipeline without your intervention. When a build breaks, the agent pulls the exact execution logs, identifies the failing commit, and locates the broken file in your current Windsurf workspace. You don't need to copy-paste stack traces from a browser tab anymore. Cascade reads the pipeline error, writes a fix in your local editor, and uses `trigger_codefresh_build` to test the correction immediately.

Inspect Pipeline Configurations and Contexts

This MCP Server exposes `get_pipeline_configuration` and `list_shared_contexts` to let Cascade inspect how your builds are wired. The agent analyzes your environment variables, secrets, and pipeline steps to find configuration drift between your local setup and the remote runner. Instead of manually hunting down missing environment variables, Windsurf compares your local `.env` files against your Codefresh shared contexts. Cascade then updates your local configuration to match what runs in production.

Monitor Kubernetes Clusters via Windsurf

This MCP integration lets Windsurf query your connected GitOps and Kubernetes environments directly from the editor using `list_delivery_clusters`. Cascade maps your local deployment files to active delivery targets, verifying that your cluster is ready for the next release. If a deployment target goes offline, Cascade flags the mismatch before you push code. You get immediate feedback on your deployment targets without leaving your editor.

Setup guide

Set up Codefresh MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Codefresh MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Codefresh payment history." If connected, Cascade will call the Codefresh tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "codefresh-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Windsurf

Add the server to your `~/.codeium/windsurf/mcp_config.json` file under the `mcpServers` key. Cascade automatically detects the new tools upon restart, or you can click refresh in the Windsurf MCP panel.

Yes. Cascade chains tools like `list_codefresh_pipelines` and `trigger_codefresh_build` to start runs when you save your work. It plans the sequence and runs the build without prompting you for every step.

Cascade calls `get_build_execution_details` to fetch the raw error logs directly into your chat. It then highlights the exact lines of code in your open editor that caused the failure.

Windsurf reads the API error returned by the server and reports the exact mismatch. It will check your user profile using `get_my_codefresh_profile` to see if your account has the correct permissions.

Yes. All pipeline configurations, build logs, and shared contexts are processed locally within Windsurf's isolated environment. Your credentials and build metadata are never stored on external servers.

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