Docker MCP toolkit

The Docker MCP toolkit is a collection of pre-built MCP servers packaged as Docker containers. These servers provide common functionality (web fetching, file system access, database operations) without requiring you to write or maintain custom MCP server code.

No custom code: Pull and run pre-configured MCP servers
Isolation: Each server runs in its own container with controlled resource limits
Community-maintained: Implementations follow the MCP specification
Portable: Works the same in development and production

This guide walks through integrating the Fetch MCP server from the Docker toolkit with an existing agent.

By the end of this guide, you will have an agent that can retrieve and analyze content from any URL through the Fetch MCP tool.

Prerequisites

Before starting, you need:

A working agent deployed with Idun (see the quickstart)
Docker Desktop installed and running

Pull the Fetch MCP server image:

docker pull mcp/fetch

Set up the Fetch MCP server

Configure Docker Desktop

Open Docker Desktop and verify:

Docker Desktop is running
The mcp/fetch image appears in the Images section

Create the MCP server in the Manager

Access the Manager web interface at http://localhost:3000.

Click MCP Servers in the main navigation
Click Create MCP Server
Fill in the configuration:

Field	Value	Description
Name	`fetch`	Identifier for this MCP server
Transport	`stdio`	Communication via standard I/O
Command	`docker`	Docker CLI command
Args	`["run", "-i", "--rm", "mcp/fetch"]`	Docker run arguments as JSON array

Click Save

The Args field must be a valid JSON array. Copy the value including brackets: ["run", "-i", "--rm", "mcp/fetch"]

The args breakdown:

run: Execute a new container
-i: Interactive mode (keeps STDIN open for MCP communication)
--rm: Remove container when it stops
mcp/fetch: The Docker image to run

Attach the MCP server to your agent

Navigate to Agents in the main navigation
Find your agent and click Edit
Scroll to the MCP Servers section
Click Add MCP Server and select fetch from the dropdown
Click Save

Integrate MCP tools in your agent code

Set the environment variables so the engine can fetch config and authenticate:

export IDUN_MANAGER_HOST="http://localhost:8080"
export IDUN_AGENT_API_KEY="YOUR_AGENT_API_KEY"

Find your agent’s API key in the Manager UI under the agent’s details page.

Import MCP tools in your agent code:

ADK
LangGraph

from google.adk.agents import LlmAgent
from idun_agent_engine.mcp import get_adk_tools
import os

os.environ["GOOGLE_GENAI_USE_VERTEXAI"] = "TRUE"
os.environ["GOOGLE_CLOUD_PROJECT"] = "your-project-id"
os.environ["GOOGLE_CLOUD_LOCATION"] = "us-central1"

def get_current_time(city: str) -> dict:
    """Returns the current time in a specified city."""
    return {"status": "success", "city": city, "time": "10:30 AM"}

idun_tools = get_adk_tools()
tools = [get_current_time] + idun_tools

root_agent = LlmAgent(
    model="gemini-2.5-flash",
    name="root_agent",
    description="Tells the current time in a specified city.",
    instruction="You are a helpful assistant.",
    tools=tools,
)

from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI
from idun_agent_engine.mcp import get_langchain_tools

model = ChatOpenAI(model="gpt-4")

mcp_tools = await get_langchain_tools()

agent = create_react_agent(
    model=model,
    tools=mcp_tools,
    state_modifier="You are a helpful assistant with access to web content fetching.",
)

get_adk_tools() and get_langchain_tools() discover all MCP servers attached to your agent and make their tools available. You do not need to configure individual tools.

Launch the agent

Navigate to your agent directory and start the engine:

idun agent serve --source manager

The engine will:

Fetch agent config from the Manager API
Initialize your agent framework
Start the Fetch MCP server as a Docker container
Register the fetch tool with your agent
Start the API server at http://localhost:8000

Test MCP integration

In the Manager UI, navigate to your agent and open the API Integration tab. Use the chat interface to test:

Give me the information on this website: https://www.idun-group.com/idun-agent-platform

Go to https://news.ycombinator.com and summarize the top 3 stories

Fetch https://github.com/trending and list the trending repositories

When you send a query, the agent recognizes it needs web content, invokes the Fetch MCP tool, and the Docker container retrieves the URL content for the agent to analyze.

Verify the MCP server

Check that the Docker container is running:

docker ps | grep mcp/fetch

View MCP server logs for debugging:

docker logs $(docker ps -q --filter ancestor=mcp/fetch)

Advanced configuration

Multiple MCP servers

Add more MCP servers through the Manager UI to give your agent access to additional tools. Filesystem access:

Field	Value
Name	`filesystem`
Transport	`stdio`
Command	`npx`
Args	`["-y", "@modelcontextprotocol/server-filesystem", "/allowed/path"]`

Allows the agent to read, write, and manipulate files within specified directories. Custom Docker MCP server:

Field	Value
Name	`custom`
Transport	`stdio`
Command	`docker`
Args	`["run", "-i", "--rm", "your-registry/your-mcp:latest"]`

Deploy your own MCP servers for database access, API integrations, or internal tools.

Troubleshooting

MCP server fails to connect

Symptoms: Agent starts but MCP tools are not available.Solutions:

Verify Docker Desktop is running: docker info
Check the image exists: docker images | grep mcp/fetch
Test the container manually: docker run -i --rm mcp/fetch
Review Docker Desktop logs

Agent does not use the fetch tool

Symptoms: Agent responds but does not fetch web content.Solutions:

Check Docker container is running: docker ps | grep mcp/fetch
Review MCP server logs: docker logs <container_id>
Try an explicit query: “Use the fetch tool to get https://example.com”
Restart the agent
Verify MCP config saved correctly in the Manager UI

Args format invalid

Symptoms: “Invalid args format” error when saving.Solution: Args must be a properly formatted JSON array.Correct:

["run", "-i", "--rm", "mcp/fetch"]

Incorrect:

run -i --rm mcp/fetch

Incorrect:

["run -i --rm mcp/fetch"]

Best practices

Naming: Use descriptive, lowercase names for MCP servers: fetch, filesystem, database
Incremental testing: Add one MCP server at a time. Test functionality before adding more
Resource limits: In production, set Docker resource constraints to prevent runaway usage:
```
["run", "-i", "--rm", "--memory=512m", "--cpus=0.5", "mcp/fetch"]
```

Logging: Configure Docker logging for better observability:

["run", "-i", "--rm", "--log-driver=json-file", "--log-opt=max-size=10m", "mcp/fetch"]

Credentials: Never hardcode sensitive information in MCP configurations. Use environment variables
Monitoring: Use observability to track MCP server latency and error rates

Getting started

Manager

Agent frameworks

Guardrails

Memory

Observability

Tool governance

Authentication

Integrations

Deployment

Advanced

Prerequisites

Set up the Fetch MCP server

Verify the MCP server

Advanced configuration

Multiple MCP servers

Troubleshooting

Best practices

Getting started

Manager

Agent frameworks

Guardrails

Memory

Observability

Tool governance

Authentication

Integrations

Deployment

Advanced

​Prerequisites

​Set up the Fetch MCP server

​Verify the MCP server

​Advanced configuration

​Multiple MCP servers

​Troubleshooting

​Best practices

Prerequisites

Set up the Fetch MCP server

Verify the MCP server

Advanced configuration

Multiple MCP servers

Troubleshooting

Best practices