How to Use the Dagger (Programmable CI) MCP in Claude

Q: Can Claude Desktop manage local build caches using the Dagger (Programmable CI) MCP Server?

Yes. The server exposes querycachevolume which Claude Desktop invokes to persist build artifacts on your machine. This speeds up consecutive pipeline runs directly from your chat interface.

Q: Does the Dagger (Programmable CI) integration with Claude Desktop support private repositories?

It does. Claude Desktop calls querygit to fetch your private code and uses querysecret to safely handle the required SSH keys or access tokens. This keeps your private code secure while building locally.

Q: How does the agent spin up containers?

The agent uses querycontainer to create a scratch container on your local engine. This MCP tool lets you run commands or inspect files as part of your pipeline run.

Run Dagger (Programmable CI) pipelines directly inside Claude Desktop to build and test code locally without switching to a terminal.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dagger (Programmable CI) MCP to Claude Desktop

Create your Vinkius account to connect Dagger (Programmable CI) to Claude Desktop 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 Dagger (Programmable CI) with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct Pipeline Execution via MCP Server

This Dagger (Programmable CI) MCP Server allows Claude Desktop to trigger pipelines directly from your chat. Ask Claude Desktop to run your Dagger builds or spin up test environments. Your agent uses `execute_graphql_query` to send commands straight to your local Dagger engine. You do not have to copy-paste terminal outputs anymore because the tool returns pipeline results directly into your chat window.

Local Resource and Cache Management

Managing local build caches becomes straightforward when Claude Desktop connects to this Dagger engine. Your desktop agent calls `query_cache_volume` to persist build outputs across runs, keeping your feedback loops incredibly short. If you need a clean slate, Claude Desktop runs `query_directory` to set up empty workspaces. The tool also calls `query_host` to inspect your local system paths, keeping your build files organized without manual cleanup.

Git and Secret Integration

Integrating Git repositories and secrets inside Claude Desktop is handled directly by this Dagger (Programmable CI) server. Your agent uses `query_git` to pull exact repository states and feeds them straight into your active pipeline. Security matters, so Claude Desktop manages sensitive variables safely. It calls `query_secret` to pass environment variables or files to your containers without exposing plain text in your chat logs.

Setup guide

Set up Dagger (Programmable CI) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Dagger (Programmable CI) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Dagger (Programmable CI) MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under dagger-programmable-ci-mcp.

json

{
  "mcpServers": {
    "dagger-programmable-ci-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 Dagger. 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 Dagger (Programmable CI) 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 Dagger (Programmable CI) MCP in Claude Desktop

Type a request like 'run my tests' in the chat. Claude Desktop uses `execute_graphql_query` to talk to your local Dagger engine, starting the build and printing the logs in real time.

Yes. The server exposes `query_cache_volume` which Claude Desktop invokes to persist build artifacts on your machine. This speeds up consecutive pipeline runs directly from your chat interface.

It does. Claude Desktop calls `query_git` to fetch your private code and uses `query_secret` to safely handle the required SSH keys or access tokens. This keeps your private code secure while building locally.

The agent uses `query_container` to create a scratch container on your local engine. This MCP tool lets you run commands or inspect files as part of your pipeline run.

All GraphQL queries and container IDs stay on your local machine. The server processes `query_secret` requests locally via stdio, meaning your API tokens and environment variables never pass through 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