Docker

Infrastructure · MCP Server

Docker MCP: setup, permissions and security risks

The Docker MCP server gives an agent containers, images, volumes, and exec. That is useful, and it is also a set of real capabilities pointed at a real system. Here is what it exposes, why it is worth governing, and the policy to put in front of it.

What the server hands your agent

Listing and inspecting containers and images, starting and stopping containers, and often exec into a running container.

Why it is worth governing

  • Exec into a container is arbitrary command execution, and it arrives dressed as a container-management tool.
  • Access to the Docker socket is, on most hosts, equivalent to root on that host.
  • Container environment variables are a standard place for credentials, and inspect returns them.

Tag what the tools actually do

Prismor tags every tool by behavior rather than by name, so rules survive a server adding tools you have never seen. A sensible starting map for Docker:

Tool patternTagsWhy
mcp__docker__exec*critical_actionexec runs arbitrary commands
mcp__docker__*inspect*secrets_accessinspect returns environment variables
mcp__docker__remove*critical_actionremoval destroys state

Patterns are illustrative globs. Run prismor tags list to see how your installed tools actually resolve.

The policy

Rules read as a sentence: a tag, then or with another tag, and what to do about it. Note the mode - start by watching, not blocking.

settings:
  tool_tags:
    enabled: true
    mode: observe            # switch to enforce once the log looks right
    tags:
      "mcp__docker__exec*": [critical_action]
      "mcp__docker__*inspect*": [secrets_access]
      "mcp__docker__remove*": [critical_action]
    rules:
      - "untrusted_content then critical_action -> block"
      - "secrets_access with external_comms -> block"

Putting Docker behind the gateway

You do not change the Docker server or how it is configured. Move your existing mcpServers block behind the Prismor gateway and point your agent at Prismor instead:

prismor mcp-gateway install    # moves your .mcp.json servers behind the gateway
prismor mcp-gateway uninstall  # restores the original, backup kept

Your agent sees the same Docker tools, namespaced as mcp__docker__<tool>. Every call is evaluated against policy before it is forwarded, and every result is scanned as untrusted content before the model sees it.

Frequently asked questions

Is the Docker MCP server safe to give an AI agent?

It is as safe as the credential behind it and the policy in front of it. The server itself is not the problem: the risk is that an agent can combine Docker access with everything else in the session, with no record of what it did. Front it with a gateway that evaluates each call and logs the verdict.

Does Prismor replace the Docker MCP server?

No. You keep running the same server, unchanged. Prismor aggregates it behind a single connector so your agent sees the same tools, namespaced as mcp__<server>__<tool>, with every call and every result passing through policy first.

Will this block work my team actually needs to do?

Not if you start in observe mode. Every call is recorded with the decision that would have applied, and nothing is blocked. You promote rules to enforce once the log shows the policy matches how your agents really work.

What about tool results, not just tool calls?

Results are scanned as untrusted content before the model sees them. A response carrying injected instructions or poisoned output is withheld and replaced with the reason, which matters most for servers that return text other people wrote.

One gateway for every MCP server

Docker is one connector. The same policy covers the rest of them, plus the shell commands and file access your agents already have.

Other infrastructure servers

Docker is a trademark of its respective owner. Prismor is not affiliated with or endorsed by it. The Docker MCP server is third-party software; Prismor governs it the same way it governs any MCP server, without modifying it.