How to Use the Codefresh MCP in Claude Code

Q: How do I install the Codefresh MCP Server for Claude Code?

Run claude mcp add --transport http codefresh-mcp -- in your terminal. This command registers the server and saves the configuration to your local /.claude.json file.

Q: Can Claude Code trigger a Codefresh build from a script?

Yes. You can run Claude Code in headless mode to execute triggercodefreshbuild as part of your terminal workflow.

Q: How does Claude Code handle failing Codefresh builds?

Claude Code calls getbuildexecutiondetails to parse the failure logs directly in your shell. It then suggests command-line fixes or edits the broken files on the spot.

Run Codefresh builds and inspect delivery clusters directly from the Claude Code terminal.

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 Claude Code

Create your Vinkius account to connect Codefresh to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger and Monitor Builds via Claude Code CLI

Claude Code uses `trigger_codefresh_build` and `list_codefresh_builds` to start and track pipeline runs directly from your command line. You can pipe the output of these tools into other CLI utilities or shell scripts for headless execution. Instead of opening a browser to check if your build passed, you ask your terminal agent to watch the run. It polls the status using `get_build_execution_details` and alerts you the second it finishes.

Inspect Pipeline Configs in Your Terminal

This MCP Server uses `get_pipeline_configuration` and `list_codefresh_pipelines` to give your terminal agent deep visibility into your CI setup. The agent can parse complex YAML definitions and find configuration errors without manual searching. If a build fails due to a syntax error, Claude Code pinpoints the exact line in your configuration. It edits the file and prepares the commit right inside your active SSH session.

Query Delivery Clusters and Shared Contexts

This MCP tool uses `list_delivery_clusters` and `list_shared_contexts` to inspect your deployment targets and environment variables from the shell. Your terminal agent checks cluster health and flags missing secrets before you trigger a deployment. This gives DevOps engineers a fast way to verify environment readiness before running production scripts. You get immediate feedback on your GitOps state without leaving the CLI.

Setup guide

Set up Codefresh MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see codefresh-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Codefresh transactions." It will automatically discover and invoke the available Codefresh tools.

Terminal

claude mcp add --transport http codefresh-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "codefresh-mcp": {
      "type": "url",
      "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 Claude Code

Run `claude mcp add --transport http codefresh-mcp -- ` in your terminal. This command registers the server and saves the configuration to your local `~/.claude.json` file.

Yes. You can run Claude Code in headless mode to execute `trigger_codefresh_build` as part of your terminal workflow.

Claude Code calls `get_build_execution_details` to parse the failure logs directly in your shell. It then suggests command-line fixes or edits the broken files on the spot.

Yes. The server supports HTTP and SSE transports, allowing you to run it locally or host it securely within your private network.

No. Your Kubernetes cluster metadata and shared contexts are processed locally on your terminal machine. The MCP integration never transmits your cluster configurations or API tokens to external logging services.

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