Prerequisites

All examples in this guide use the public image. If you’ve mirrored the repository for your own use (for example, to your Docker Hub namespace), update your commands to reference the mirrored image instead of the public one.

For example:

• Public image: dhi.io/<repository>:<tag>
• Mirrored image: <your-namespace>/dhi-<repository>:<tag>

For the examples, you must first use docker login dhi.io to authenticate to the registry to pull the images.

Getting Started with Memory MCP Server

The Memory MCP Server provides ephemeral and persistent memory tools for MCP clients, enabling AI applications to store and retrieve contextual information across sessions for enhanced conversational capabilities.

Configuration

Claude Desktop Configuration

For ephemeral memory (stored in container):

{
  "mcpServers": {
    "memory": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "dhi.io/memory-mcp"
      ]
    }
  }
}

For persistent memory (stored on host):

{
  "mcpServers": {
    "memory": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-v", "/path/to/memory/data:/memory:rw",
        "dhi.io/memory-mcp",
        "/memory"
      ]
    }
  }
}

Replace /path/to/memory/data with your desired storage location.

Running the Server

Ephemeral memory (lost when container stops):

docker run --rm -i \
  dhi.io/memory-mcp

Persistent memory (survives container restarts):

docker run --rm -i \
  -v "$HOME/.memory:/memory:rw" \
  dhi.io/memory-mcp \
  /memory

Available Tools

The Memory MCP Server provides the following capabilities:

Memory Storage:

• Store key-value pairs
• Save complex data structures
• Organize memories with tags and categories
• Set memory priorities and relevance

Memory Retrieval:

• Retrieve specific memories by key
• Search memories by tags or categories
• Query memories by relevance to current context
• List all stored memories

Memory Management:

• Update existing memories
• Delete individual memories
• Clear all memories
• Set memory expiration (if supported)

Memory Types

Ephemeral Memory:

• Stored only during the session
• Lost when container stops
• Useful for temporary context
• No persistence overhead

Persistent Memory:

• Survives container restarts
• Stored on the host filesystem
• Enables long-term context retention
• Requires volume mount

Example Use Cases

User Preferences

Query: "Remember that I prefer dark mode"
Server stores preference for future sessions

Project Context

Query: "Remember that we're working on the authentication feature"
Server maintains project context across conversations

Learning from Interactions

Query: "What coding style did we agree on?"
Server retrieves previously stored style guidelines

Cross-Session Continuity

Query: "What were we discussing last time?"
Server retrieves recent conversation context

Task Tracking

Query: "Remember to update the documentation after deployment"
Server stores task reminder for future reference

Security Considerations

Security recommendations:

1. Access Control: Restrict access to memory storage directories
2. Encryption: Consider encrypting the volume for sensitive data
3. Data Privacy: Be mindful of what information is stored in memory
4. Backup Strategy: Implement backups for important persistent memory
5. Cleanup Policy: Regularly review and clean up stored memories

Storage Management

Backing Up Memory:

# Backup memory data
tar -czf memory-backup.tar.gz /path/to/memory/data

Restoring Memory:

# Restore memory data
tar -xzf memory-backup.tar.gz -C /path/to/memory/data

Clearing All Memory:

# Remove all stored memories
rm -rf /path/to/memory/data/*

Performance Tips

• Use ephemeral memory for temporary, session-specific data
• Use persistent memory for long-term context that should survive restarts
• Organize memories with clear keys and tags for efficient retrieval
• Periodically clean up outdated memories to maintain performance
• Consider memory size when storing large data structures

Memory Organization Best Practices

1. Use Descriptive Keys: Name memories with clear, descriptive keys
2. Categorize: Use tags or categories to organize related memories
3. Prioritize: Mark important memories for quick retrieval
4. Lifecycle Management: Remove obsolete memories regularly
5. Context Separation: Use different memory stores for different projects or contexts

Integration Patterns

Personal Assistant:

Store user preferences, habits, and recurring tasks
Retrieve context for personalized responses

Development Assistant:

Remember project structure, coding conventions, and decisions
Maintain context about ongoing work and future tasks

Research Assistant:

Store research findings, references, and notes
Build a knowledge base across multiple research sessions

Additional Resources

• Memory MCP Server Documentation⁠
• Model Context Protocol⁠
• MCP Servers Repository⁠

Non-hardened images vs Docker Hardened Images

Key differences

Why no shell or package manager?

Docker Hardened Images prioritize security through minimalism:

• Reduced attack surface: Fewer binaries mean fewer potential vulnerabilities
• Immutable infrastructure: Runtime containers shouldn't be modified after deployment
• Compliance ready: Meets strict security requirements for regulated environments

The hardened images intended for runtime don't contain a shell nor any tools for debugging. Common debugging methods for applications built with Docker Hardened Images include:

• Docker Debug⁠ to attach to containers
• Docker's Image Mount feature to mount debugging tools
• Ecosystem-specific debugging approaches

Docker Debug provides a shell, common debugging tools, and lets you install other tools in an ephemeral, writable layer that only exists during the debugging session.

For example, you can use Docker Debug:

docker debug <container-name>

or mount debugging tools with the Image Mount feature:

docker run --rm -it --pid container:my-memory-mcp \
  --mount=type=image,source=dhi.io/busybox,destination=/dbg,ro \
  dhi.io/memory-mcp:<tag> /dbg/bin/sh

Image variants

Docker Hardened Images come in different variants depending on their intended use.

Runtime variants are designed to run your application in production. These images are intended to be used either directly or as the FROM image in the final stage of a multi-stage build. These images typically:

• Run as the nonroot user
• Do not include a shell or a package manager
• Contain only the minimal set of libraries needed to run the app

Build-time variants typically include dev in the variant name and are intended for use in the first stage of a multi-stage Dockerfile. These images typically:

• Run as the root user
• Include a shell and package manager
• Are used to build or compile applications

FIPS variants

FIPS variants include fips in the variant name and tag. They come in both runtime and build-time variants. These variants use cryptographic modules that have been validated under FIPS 140, a U.S. government standard for secure cryptographic operations.

For example, usage of MD5 fails in FIPS variants. To verify FIPS compliance, check the cryptographic module version in use by your Argo CD instance.

Migrate to a Docker Hardened Image

To migrate your application to a Docker Hardened Image, you must update your Dockerfile. At minimum, you must update the base image in your existing Dockerfile to a Docker Hardened Image. This and a few other common changes are listed in the following table of migration notes:

The following steps outline the general migration process.

1. Find hardened images for your app.

   A hardened image may have several variants. Inspect the image tags and find the image variant that meets your needs.

2. Update the base image in your Dockerfile.

   Update the base image in your application's Dockerfile to the hardened image you found in the previous step. For framework images, this is typically going to be an image tagged as dev because it has the tools needed to install packages and dependencies.

3. For multi-stage Dockerfiles, update the runtime image in your Dockerfile.

   To ensure that your final image is as minimal as possible, you should use a multi-stage build. All stages in your Dockerfile should use a hardened image. While intermediary stages will typically use images tagged as dev, your final runtime stage should use a non-dev image variant.

4. Install additional packages

   Docker Hardened Images contain minimal packages in order to reduce the potential attack surface. You may need to install additional packages in your Dockerfile. Inspect the image variants to identify which packages are already installed.

   Only images tagged as dev typically have package managers. You should use a multi-stage Dockerfile to install the packages. Install the packages in the build stage that uses a dev image. Then, if needed, copy any necessary artifacts to the runtime stage that uses a non-dev image.

   For Alpine-based images, you can use apk to install packages. For Debian-based images, you can use apt-get to install packages.

Troubleshoot migration

General debugging

The hardened images intended for runtime don't contain a shell nor any tools for debugging. The recommended method for debugging applications built with Docker Hardened Images is to use Docker Debug⁠ to attach to these containers. Docker Debug provides a shell, common debugging tools, and lets you install other tools in an ephemeral, writable layer that only exists during the debugging session.

Permissions

By default image variants intended for runtime, run as the nonroot user. Ensure that necessary files and directories are accessible to the nonroot user. You may need to copy files to different directories or change permissions so your application running as the nonroot user can access them.

Privileged ports

Non-dev hardened images run as a nonroot user by default. As a result, applications in these images can't bind to privileged ports (below 1024) when running in Kubernetes or in Docker Engine versions older than 20.10.

No shell

By default, image variants intended for runtime don't contain a shell. Use dev images in build stages to run shell commands and then copy any necessary artifacts into the runtime stage. In addition, use Docker Debug to debug containers with no shell.

Entry point

Docker Hardened Images may have different entry points than images such as Docker Official Images. Use docker inspect to inspect entry points for Docker Hardened Images and update your Dockerfile if necessary.