What is the Dagger MCP used for?

It allows your AI agent to orchestrate delivery pipelines by interacting with the Dagger Engine's GraphQL API.

Do I need to run Dagger locally?

Yes, you must ensure a Dagger Engine is running in your environment and provide the session port and token to the MCP.

Can my agent run container operations?

Yes, the MCP includes capabilities to initialize scratch containers and manage OCI-compatible states.

How does the agent handle secrets?

The agent can create new secrets using values from environment variables, files, or command outputs.

Which AI clients can use this MCP?

Any MCP-compatible client like Claude, Cursor, Windsurf, or VS Code can use this MCP.

How do I run a specific build command using Dagger?

You can use the execute_graphql_query capability to send a raw GraphQL query to the Dagger engine, allowing you to chain container operations like from, withExec, and stdout.

Can I access files from my local machine in the pipeline?

Yes, the query_host capability allows you to retrieve the state ID for your host environment, which can then be used to mount local directories into your Dagger containers.

How are secrets handled in this integration?

Use the query_secret capability to load secrets from URIs (like env:// or file://). This returns a secret ID that can be safely passed to other Dagger operations without exposing the plaintext value.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Dagger Programmable Ci to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Orchestrate complex delivery pipelines using natural language.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Dagger.

01
Query cache volume
This capability builds a cache volume for your operations. Use it to persist data across different pipeline steps.
02
Query container
This capability creates a new scratch container. It returns a unique ID you can use to chain further actions.
03
Query directory
This capability initializes an empty directory. It provides a directory ID for managing files within your pipeline.
04
Query host
This capability queries the host environment. Use it to check the local system state during execution.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Dagger.

05
Query git
This capability interacts with Git repositories. It allows your agent to pull source code into the pipeline.
06
Execute graphql query
This capability runs raw GraphQL queries against the Dagger engine. You can use it to chain fields and create a DAG of operations.
07
Query current module
This capability inspects the current module. It helps your agent understand the context of the active Dagger module.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Dagger.

08
Query http
This capability fetches files from a URL. It returns the requested file directly to your agent.
09
Query secret
This capability creates a new secret. You can pull values from environment variables, files, or command outputs.
10
Query version
This capability checks the Dagger Engine version. Use it to ensure your environment matches your requirements.

Real work

What teams actually run

Automated Pipeline Debugging

An engineer asks the agent to find why a build failed by inspecting the engine state.

Dynamic Build Orchestration

The agent composes a new test suite by chaining GraphQL queries to create a DAG.

Containerized Testing

A developer instructs the agent to spin up a scratch container to run a specific test suite.

Secret Management

The agent creates and uses secrets from environment variables to secure a deployment.

Automate a task

Put Dagger to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Dagger works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Dagger to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1002ms average. Fast in production.

Dagger is checked daily against the live service.

Daily averagePeak 1256ms

Oct 3Today

Fastest day: 736ms
Slowest day: 1256ms
14-day trend: Improving-7%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Dagger, so you can see the experience inside your AI.

It does not authenticate your account with Dagger. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Dagger Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_jU749naeDKubVrRR38BTiJPB8XzxtT6YXppJtFAW/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Dagger capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "dagger-programmable-ci-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_jU749naeDKubVrRR38BTiJPB8XzxtT6YXppJtFAW/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Dagger in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Dagger owners hand off.

This MCP is built for technical professionals who want to bridge the gap between natural language and programmable CI/CD.

01
DevOps Engineers
They hand off pipeline debugging and execution tasks to the agent.
02
Software Developers
They run builds and container operations directly from their code editor.
03
SREs
They use the agent to inspect engine states and orchestrate infrastructure tasks.

FAQ

Questions Dagger owners ask.

01
What is the Dagger MCP used for?
It allows your AI agent to orchestrate delivery pipelines by interacting with the Dagger Engine's GraphQL API.
02
Do I need to run Dagger locally?
Yes, you must ensure a Dagger Engine is running in your environment and provide the session port and token to the MCP.
03
Can my agent run container operations?
Yes, the MCP includes capabilities to initialize scratch containers and manage OCI-compatible states.
04
How does the agent handle secrets?
The agent can create new secrets using values from environment variables, files, or command outputs.
05
Which AI clients can use this MCP?
Any MCP-compatible client like Claude, Cursor, Windsurf, or VS Code can use this MCP.
06
How do I run a specific build command using Dagger?
You can use the execute_graphql_query capability to send a raw GraphQL query to the Dagger engine, allowing you to chain container operations like from, withExec, and stdout.
07
Can I access files from my local machine in the pipeline?
Yes, the query_host capability allows you to retrieve the state ID for your host environment, which can then be used to mount local directories into your Dagger containers.
08
How are secrets handled in this integration?
Use the query_secret capability to load secrets from URIs (like env:// or file://). This returns a secret ID that can be safely passed to other Dagger operations without exposing the plaintext value.

Explore

More in Loved By Devs

Connect Dagger to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Query cache volume

Query container

Query directory

Query host

05-07

Query git

Execute graphql query

Query current module

08-10

Query http

Query secret

Query version

What teams actually run

Automated Pipeline Debugging

Dynamic Build Orchestration

Containerized Testing

Secret Management

Building your own app? The connector is yours to use.

Dagger Connector

Claude Desktop

DevOps Engineers

Software Developers

SREs

What is the Dagger MCP used for?

Do I need to run Dagger locally?

Can my agent run container operations?

How does the agent handle secrets?

Which AI clients can use this MCP?

How do I run a specific build command using Dagger?

Can I access files from my local machine in the pipeline?

How are secrets handled in this integration?

Codefresh AI Connector

Buildkite AI Connector

CircleCI AI Connector

Codecov AI Connector

Suggestions

Hevo Data (ETL & Data Pipeline) AI Connector

Argo Workflows AI Connector

Porter PaaS AI Connector

Code Integrity Prover AI Connector