MCP

Dagger can be used as a programming environment for AI agents. Dagger provides an LLM core type that enables native integration of Large Language Models (LLM) in your workflows.

Model Context Protocol (MCP) support in Dagger can be broken into three categories:

1. MCP within Dagger
2. Exposing MCP outside of Dagger
3. Connecting to external MCP from Dagger

MCP within Dagger

A key feature of Dagger's LLM integration is out-of-the-box support for MCP using Dagger Functions: an LLM can automatically discover and use any available Dagger Functions in your Module.

LLM Bindings

Here's an example of Dagger's LLM bindings in action:

Dagger Shell

First type 'dagger' for interactive mode.

llm | with-container $(container | from alpine) | with-prompt "You have an alpine container. Install tools to develop with Python." | container | terminal

System shell

dagger <<EOF
llm |
  with-container \$(container | from alpine) |
  with-prompt "You have an alpine container. Install tools to develop with Python." |
  container |
  terminal
EOF

Agent loop

Consider the following Dagger Function:

Go

package main

import (
	"dagger/coding-agent/internal/dagger"
)

type CodingAgent struct{}

// Write a Go program
func (m *CodingAgent) GoProgram(
	// The programming assignment, e.g. "write me a curl clone"
	assignment string,
) *dagger.Container {
	workspace := dag.ToyWorkspace()
	environment := dag.Env().
		WithToyWorkspaceInput("before", workspace, "tools to complete the assignment").
		WithStringInput("assignment", assignment, "the assignment to complete").
		WithToyWorkspaceOutput("after", "the completed assignment")

	return dag.LLM().
		WithEnv(environment).
		WithPrompt(`
			You are an expert go programmer. You have access to a workspace.
			Use the default directory in the workspace.
			Do not stop until the code builds.
			Your assignment is: $assignment`).
		Env().
		Output("after").
		AsToyWorkspace().
		Container()
}

Python

import dagger
from dagger import dag, function, object_type


@object_type
class CodingAgent:
    @function
    def go_program(
        self,
        assignment: str,
    ) -> dagger.Container:
        """Write a Go program"""
        workspace = dag.toy_workspace()
        environment = (
            dag.env()
            .with_toy_workspace_input(
                "before", workspace, "tools to complete the assignment"
            )
            .with_string_input("assignment", assignment, "the assignment to complete")
            .with_toy_workspace_output("after", "the completed assignment")
        )

        return (
            dag.llm()
            .with_env(environment)
            .with_prompt(
                """
            You are an expert go programmer. You have access to a workspace.
            Use the default directory in the workspace.
            Do not stop until the code builds.
            Your assignment is: $assignment"""
            )
            .env()
            .output("after")
            .as_toy_workspace()
            .container()
        )

TypeScript

import { dag, object, func, Container } from "@dagger.io/dagger"

@object()
export class CodingAgent {
  /**
   * Write a Go program
   */
  @func()
  goProgram(
    /**
     * The programming assignment, e.g. "write me a curl clone"
     */
    assignment: string,
  ): Container {
    const workspace = dag.toyWorkspace()
    const environment = dag
      .env()
      .withToyWorkspaceInput(
        "before",
        workspace,
        "tools to complete the assignment",
      )
      .withStringInput("assignment", assignment, "the assignment to complete")
      .withToyWorkspaceOutput("after", "the completed assignment")

    return dag
      .llm()
      .withEnv(environment)
      .withPrompt(`
        You are an expert go programmer. You have access to a workspace.
  			Use the default directory in the workspace.
  			Do not stop until the code builds.
  			Your assignment is: $assignment
			`)
      .env()
      .output("after")
      .asToyWorkspace()
      .container()
  }
}

This Dagger Function creates a new LLM, gives it an environment (a container with various tools) with an assignment, and prompts it to complete the assignment. The LLM then runs in a loop, calling tools and iterating on its work, until it completes the assignment. This loop all happens inside of the LLM object, so the value of result is the environment with the completed assignment.

Exposing MCP outside of Dagger

Dagger has built-in MCP support that allows you to easily expose Dagger modules as an MCP server. This allows you to configure a client (such as Claude Desktop, Cursor, Goose CLI/Desktop) to consume modules from the Daggerverse or any git repo as native MCP servers.

warning

Today only modules with no required constructor arguments are supported when exposing an MCP server outside of Dagger.

Connecting to External MCP Server from Dagger

Support for connecting to external MCP servers from Dagger is coming soon.

Learn more

• Build an AI agent with our quickstart
• Browse AI agent examples
• Learn about the agent loop and how to work with LLM prompts and responses
• Configure LLM endpoints