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

Q: How do I add the Dagger (Programmable CI) server to Claude Code?

Run claude mcp add --transport http dagger -- in your terminal. You can verify the installation by running claude mcp list to see the registered GraphQL and container tools.

Q: Can Claude Code execute complex build DAGs via Dagger (Programmable CI)?

Yes, the agent calls the executegraphqlquery tool to chain multiple pipeline steps together. It can construct and run entire Directed Acyclic Graphs directly through your local engine.

Q: How does Claude Code handle build caching with Dagger (Programmable CI)?

Claude Code uses querycachevolume to mount persistent cache directories. This ensures that compiler caches, library folders, and dependencies are preserved across separate runs in your terminal session.

Drive your programmable Dagger pipelines directly from your terminal using Claude Code.

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 Code

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run raw GraphQL pipeline queries from Claude Code.

This MCP Server exposes the `execute_graphql_query` tool to let Claude Code interact directly with your local Dagger Engine. You can pipe terminal commands into your agent, and it will execute complex pipeline DAGs without needing a heavy GUI or web console. The agent checks your current environment version using `query_version` to ensure compatibility before running any operations. This gives you a fast, command-line-driven interface for debugging and executing containerized pipelines.

Provision scratch containers and directories.

The `query_container` tool allows Claude Code to instantiate disposable environments for testing scripts or compiling code. This MCP integration lets you spin up a scratch container, mount the workspace, and execute the commands instantly. To keep things organized, Claude Code uses `query_directory` to create empty directories on the fly. It can run compilation steps inside these isolated paths, preventing temporary build junk from polluting your main project folders.

Inject secrets and fetch remote assets.

Use the MCP connection to run `query_secret` to securely pass sensitive credentials like SSH keys or deployment tokens into your containerized steps. Claude Code can resolve environment variables or local files using this tool, ensuring secrets are only exposed inside the runtime. When your pipeline depends on remote sources, the agent calls `query_http` to pull files from public URLs directly into the container. It pairs this with `query_git` to fetch specific repository states, making your terminal-driven builds highly reproducible.

Setup guide

Set up Dagger (Programmable CI) 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 dagger-programmable-ci-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Dagger (Programmable CI) transactions." It will automatically discover and invoke the available Dagger (Programmable CI) tools.

Terminal

claude mcp add --transport http dagger-programmable-ci-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 Dagger (Programmable CI) 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": {
    "dagger-programmable-ci-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 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 Code

Run `claude mcp add --transport http dagger -- ` in your terminal. You can verify the installation by running `claude mcp list` to see the registered GraphQL and container tools.

Yes, the agent calls the `execute_graphql_query` tool to chain multiple pipeline steps together. It can construct and run entire Directed Acyclic Graphs directly through your local engine.

Claude Code uses `query_cache_volume` to mount persistent cache directories. This ensures that compiler caches, library folders, and dependencies are preserved across separate runs in your terminal session.

Yes, because Claude Code is terminal-only, you can run it inside SSH sessions, Docker containers, or GitHub Actions. It interacts with the server over standard HTTP or stdio transports to run your pipelines.

The server manages local resource states, Git metadata, and environment secrets. Because all operations run through your local Dagger Engine, your raw source code, repository credentials, and environment variables never leave your local host or secure execution environment.

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