MCP For Claude Marketplace
Dagger (Programmable CI)

Dagger (Programmable CI) MCP Connector for Claude

A+

Build, test, and deploy using Dagger's programmable CI engine. Execute GraphQL queries, manage containers, and orchestrate pipelines directly from your AI agent.

10 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect to the Dagger Engine to orchestrate your delivery pipelines using a powerful, programmable GraphQL API. This server allows your AI agent to interact directly with Dagger's Directed Acyclic Graph (DAG) of operations.

What you can do

  • Container Orchestration — Initialize scratch containers, pull images, and manage OCI-compatible states.
  • GraphQL Workflows — Execute raw GraphQL queries to compose complex build and test logic dynamically.
  • Source Control — Query Git repositories and host environments to pull source code into your pipelines.
  • Resource Management — Handle secrets securely, manage persistent cache volumes, and fetch remote files via HTTP.
  • Module Inspection — Query the current module state and engine version to ensure environment consistency.

How it works

  1. Ensure a Dagger Engine is running in your environment.
  2. Provide the session port and token generated by the Dagger CLI.
  3. Start building and deploying through natural language commands.

Who is this for?

  • DevOps Engineers — Automate pipeline debugging and execution without leaving the chat interface.
  • Software Developers — Run builds, tests, and container operations directly from the code editor.
  • SREs — Inspect engine states and orchestrate infrastructure tasks using programmable CI logic.
ci-cdcontainer-orchestrationpipeline-automationgraphqlinfrastructure-as-codebuild-automation

10 tools expose this connector's capabilities to your AI agent.

execute_graphql_query

You can chain fields to create a Directed Acyclic Graph (DAG) of operations. Execute a raw GraphQL query against the Dagger engine

query_cache_volume

Constructs a cache volume

query_container

Creates a scratch container and returns its ID

query_current_module

Queries the current module

query_directory

Creates an empty directory and returns its ID

query_git

Queries a Git repository

query_host

Queries the host environment

query_http

Returns a file from a URL

query_secret

g., env://VAR_NAME, file://PATH, cmd://COMMAND). Creates a new secret

query_version

Get the Dagger Engine version

See how to talk to your AI agent using Dagger (Programmable CI).

Check the current version of the Dagger engine.

I'll check that for you. The local Dagger engine is running version v0.12.5.

Initialize a scratch container and return its ID.

I've initialized a new scratch container. The state ID is `cont-abc123xyz`. You can now use this ID to chain further operations.

Get the state of the git repository at https://github.com/dagger/dagger.

Querying the repository... I've retrieved the state for the Dagger repository. The directory ID is `dir-repo789`. Would you like to list its contents?

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

Related Connectors

GA

Gandi.net (Domain Registration & Hosting API) MCP

14 tools Official

Manage Gandi.net domains, DNS records, mailboxes, and hosting instances directly from your AI agent.

A+ View details →
BR

Braze MCP

10 tools Official

Manage customer engagement via Braze — track users, list campaigns, and trigger canvases directly from any AI agent.

A+ View details →
WI

Wiktionary MCP

2 tools Official

Universal linguistic intelligence — get word definitions, etymologies, and examples via AI.

A+ View details →
OB

OFX Bank Statement Parser MCP

1 tools Official

Turn archaic OFX/QFX bank exports into clean JSON transactions safely and local. Let your AI act as your personal accountant without uploading sensitive financial data.

F View details →