Integrate Dagger (Programmable CI) with Claude, Cursor, Chatbots & AI Agents MCP Server

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

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

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

GDPR Free for Subscribers

Compatible with every major AI agent and IDE

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

+ other MCP clients

execute

Execute graphql query on Dagger (Programmable CI)

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

query

Query cache volume on Dagger (Programmable CI)

Constructs a cache volume

query

Query container on Dagger (Programmable CI)

Creates a scratch container and returns its ID

query

Query current module on Dagger (Programmable CI)

Queries the current module

query

Query directory on Dagger (Programmable CI)

Creates an empty directory and returns its ID

query

Query git on Dagger (Programmable CI)

Queries a Git repository

query

Query host on Dagger (Programmable CI)

Queries the host environment

query

Query http on Dagger (Programmable CI)

Returns a file from a URL

query

Query secret on Dagger (Programmable CI)

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

query

Query version on Dagger (Programmable CI)

Get the Dagger Engine version

Security & Code Integrity Audit

Every tool in the Dagger (Programmable CI) MCP Server is continuously audited by the Vinkius Security Engine. We guarantee zero-trust payload isolation, strict data boundaries, and deterministic execution for enterprise-grade AI agents.

A+Score: 100

How Vinkius protects your data

Is there a risk of the AI "going crazy" and deleting important company data?

No. With Vinkius, the AI operates on "rails". It can only make the exact moves you authorized in the tool's settings. It cannot invent routes, access other networks in your company, or decide to delete random files. If the action isn't in the approved catalog, the attempt is blocked instantly.

Can I set different limits for each virtual assistant on my team?

Absolutely. You have full control in our command center. You can create an AI agent that only "reads" data so the support team can answer questions, and another superpowered agent that can "edit" and "create" information exclusively for your operations team. Each AI gets exactly the level of access you allow.

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

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

Does the AI train on my tools or API data?

No. Vinkius enforces a strict Zero-Retention policy. Your data simply passes through our secure servers to complete the requested action and is instantly forgotten. Nothing you do here is ever stored, logged, or used to train any artificial intelligence.

Dagger (Programmable CI) Capabilities for AI Assistants

Use Dagger (Programmable CI) with any AI agent framework to process, analyze, and mutate data securely via the Model Context Protocol.

Claude Code Integration for ci cd

Integrate Dagger (Programmable CI) to access native ci cd capabilities. This allows LLMs to perform secure, deterministic execution of loved by devs tasks without hard-coded API scripts.

LLM Orchestration for container orchestration

The Dagger (Programmable CI) MCP translates LLM intent into specific container orchestration actions. Agents like Cursor use this to interface securely with your loved by devs infrastructure.