Codefresh Connector for AI agents.
8 live capabilities
Manage CI/CD pipelines and Kubernetes clusters from your chat interface.
Waiting for input…
Why people use Codefresh
Manage Codefresh CI/CD Pipelines Without Leaving Your IDE
This Connector changes that by bringing the Codefresh dashboard into your chat. You can ask your agent to check a pipeline status or trigger a build while you're still focused on your code. You get immediate answers without the friction of manual navigation.
What Vinkius changes
You get a direct command line for your CI/CD operations inside your AI chat.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Failed production build
A developer sees a red light and asks their agent to check the status of the last api-service build using get_build_execution_details.
- Real-world use case 02
Quick branch deploy
A dev wants to test a feature and asks the agent to trigger a build for the frontend pipeline on the 'feature-x' branch.
- Real-world use case 03
Infrastructure audit
A manager needs to know where things are deployed and asks the agent to list all connected Kubernetes clusters.
Complete set · 8capabilities
The complete Codefresh capability set.
These are the exact actions your AI can choose when you ask it to work with Codefresh.
01—04
4 capabilities in this set.
Part of 8 available through Codefresh.
- 01 Capability
Get build execution details
Get the specific status and execution info for a single build. This helps you see exactly where a workflow stalled.
- 02 Capability
Get my codefresh profile
Pull your account and user details. Use this to confirm which account your agent is currently authenticated with.
- 03 Capability
Get pipeline configuration
View the full configuration of a specific pipeline. It's the best way to check your current CI/CD rules without leaving your chat.
- 04 Capability
List codefresh pipelines
List every CI/CD pipeline in your account. Use this to find the right pipeline name before triggering a build.
05—08
4 capabilities in this set.
Part of 8 available through Codefresh.
- 05 Capability
List codefresh builds
See a list of all recent builds in your account. This gives you a quick overview of your recent deployment activity.
- 06 Capability
Trigger codefresh build
Start a new build for a specific pipeline. You can specify branches or variables to run a specific test or deployment.
- 07 Capability
List delivery clusters
See all connected Kubernetes and delivery clusters. This keeps your infrastructure targets visible to your agent.
- 08 Capability
List shared contexts
View shared environment contexts like secrets and variables. This is essential for auditing what's available in your workflows.
Set up in minutes
One URL. Then ask Codefresh to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Codefresh from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_PdvyiuNy98nJgJhF2rWbswmgtQCEOaod7r7AsNCv/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Codefresh, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Codefresh for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_PdvyiuNy98nJgJhF2rWbswmgtQCEOaod7r7AsNCv/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Codefresh URL.
- Step 03
Save and start
Save the connection and enable Codefresh in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"codefresh": {
"url": "https://edge.vinkius.com/vk_preview_PdvyiuNy98nJgJhF2rWbswmgtQCEOaod7r7AsNCv/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Codefresh
Open Agent mode in chat and ask: "Using Codefresh, help me...". 8 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"codefresh": {
"url": "https://edge.vinkius.com/vk_preview_PdvyiuNy98nJgJhF2rWbswmgtQCEOaod7r7AsNCv/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Codefresh
Ask Copilot: "Using Codefresh, help me...". 8 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"codefresh": {
"url": "https://edge.vinkius.com/vk_preview_PdvyiuNy98nJgJhF2rWbswmgtQCEOaod7r7AsNCv/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Codefresh
Open Cascade and ask: "Using Codefresh, help me...". 8 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"codefresh": {
"url": "https://edge.vinkius.com/vk_preview_PdvyiuNy98nJgJhF2rWbswmgtQCEOaod7r7AsNCv/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Codefresh
Ask Cline: "Using Codefresh, help me...". 8 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add codefresh --transport http "https://edge.vinkius.com/vk_preview_PdvyiuNy98nJgJhF2rWbswmgtQCEOaod7r7AsNCv/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Codefresh
Ask Claude: "Using Codefresh, show me...". 8 tools are ready
Where the request belongs
Work Codefresh can move forward.
This is for the DevOps engineer who's tired of clicking through dashboards at 2am to check if a build passed. It's for anyone who needs to keep the shipping pipeline moving without the friction of manual status checks.
DevOps Engineer
Triggers manual builds and checks pipeline health during production incidents.
Release Manager
Audits deployment success rates and cluster connectivity across different environments.
Software Developer
Quickly verifies if their latest branch build succeeded or needs a fix.
Infrastructure Engineer
Monitors Kubernetes cluster health and verifies GitOps delivery targets.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsCircleCI
Manage CI/CD pipelines and workflows via CircleCI. track jobs, trigger pipelines, and monitor build status directly from any AI agent.
Travis CI
Manage CI/CD pipelines, trigger custom builds, and oversee repository testing health securely via your AI agent.
Buildkite
Automate CI/CD pipelines via Buildkite. manage builds, agents, and deployments directly from any AI agent.
Semaphore
Automate CI/CD workflows, manage pipelines, and monitor build jobs directly from your AI agent.
Harness
Automate CI/CD and DevOps workflows via Harness. manage pipelines, executions, and secrets directly from any AI agent.
Woodpecker CI
Manage your Woodpecker CI instance. control pipelines, monitor agents, and configure repositories directly from your AI agent.
Bring your own AI
Change the model, client or framework. Keep Codefresh connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Codefresh.
The practical details behind the request, access and result.
Can I use the Codefresh MCP to start new builds?
Yes, you can trigger new builds for any of your pipelines by simply asking your agent to do so. You can even specify which branch to use or provide custom variables for the build.
Does the Codefresh MCP show me my Kubernetes clusters?
It does. You can ask your agent to list all connected delivery clusters to see exactly where your deployments are landing.
Can I check my pipeline configurations using this?
Yes, you can retrieve detailed information for any specific pipeline. This is great for verifying your CI/CD rules without having to open the Codefresh dashboard.
How do I see the status of a failed build?
You can ask your agent to get the execution details for a specific build. It will pull the status and execution info so you can see what went wrong.
Can this Connector access my secrets?
It can list your shared context, which includes the secrets and variables used in your workflows. This helps you audit what's available for your deployments.
What happens when I connect Codefresh to my AI agent?
It gives your agent the ability to interact with your CI/CD workflows. You can then manage builds, check cluster health, and audit your environment directly through your chat interface.
Can I trigger a pipeline run for a specific branch?
Yes! Use the trigger_codefresh_build capability. You can provide the pipeline ID and specify the branch name in the payload. The agent will instruct Codefresh to start the build immediately.
How do I see the status of all my Kubernetes clusters in Codefresh?
Use the list_delivery_clusters capability. Your agent will fetch all connected clusters, showing you which targets are available for deployment and their current health status.
Where do I find my Codefresh API Key?
Log in to Codefresh, click on your profile icon, go to User Settings, and select API Keys. You can generate and copy a new token from that section.
One connection away
Give your agent a direct line to Codefresh.
Connect Codefresh once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available