// SCAN REPORT

Docker

56 tools. 27 can modify or destroy data without limits.

10 destructive tools with no built-in limits. Policy required.

Last updated: 3 Apr 2026

27 can modify or destroy data

29 read-only

56 tools total

// TOOL MAP

Read (29) Write / Execute (17) Destructive / Financial (10)

// WHAT CAN GO WRONG

Destructive tools (docker_compose_down, docker_prune_containers, docker_prune_images) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (docker_connect_container, docker_create_container, docker_create_network) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (docker_compose_build, docker_compose_restart, docker_compose_start) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and Docker. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @alisaitteke/docker-mcp

Scans every tool. Generates a policy. Starts enforcing.

Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client

// RECOMMENDED RULES

Deny destructive operations

docker_compose_down:
  rules:
    - action: deny

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

docker_connect_container:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

docker_compose_config:
  rules:
    - rate_limit: 60/minute

Controls API costs and prevents retry loops from exhausting upstream rate limits.

// ALL 56 DOCKER TOOLS

DESTRUCTIVE 10 tools

Destructive docker_compose_down Destructive docker_prune_containers Destructive docker_prune_images Destructive docker_prune_networks Destructive docker_prune_system Destructive docker_prune_volumes Destructive docker_remove_container Destructive docker_remove_image Destructive docker_remove_network Destructive docker_remove_volume

EXECUTE 9 tools

Execute docker_compose_build Execute docker_compose_restart Execute docker_compose_start Execute docker_compose_stop Execute docker_compose_up Execute docker_exec Execute docker_restart_container Execute docker_start_container Execute docker_stop_container

WRITE 8 tools

Write docker_connect_container Write docker_create_container Write docker_create_network Write docker_create_volume Write docker_disconnect_container Write docker_push_image Write dockerhub_push Write ghcr_push

// FAQ

Can an AI agent delete data through the Docker MCP server? +

Yes. The Docker server exposes 10 destructive tools including docker_compose_down, docker_prune_containers, docker_prune_images. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Docker? +

The Docker server has 8 write tools including docker_connect_container, docker_create_container, docker_create_network. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the Docker MCP server expose? +

56 tools across 4 categories: Destructive, Execute, Read, Write. 29 are read-only. 27 can modify, create, or delete data.

How do I add Intercept to my Docker setup? +

One line change. Instead of running the Docker server directly, prefix it with Intercept: intercept -c io-github-alisaitteke-docker-mcp.yaml -- npx -y @@alisaitteke/docker-mcp. Download a pre-built policy from policylayer.com/policies/io-github-alisaitteke-docker-mcp and adjust the limits to match your use case.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init

Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.

Docker

One command. Full control.

Other MCP servers with similar tools.

Control every MCP tool call your agent makes.

Control every MCP tool call
your agent makes.