Manage Docker containers, images, networks, and volumes
AI agents invoke docker_manage to trigger actions in MCP Workspace Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Docker management encompasses executing containers (running arbitrary code/processes), controlling networks, and managing volumes. This can have significant blast radius as it can start new processes, expose network services, or manipulate data volumes.
From the tool's definition 'Manage Docker containers, images, networks, and volumes' — managing Docker resources involves starting/stopping containers, pulling/running images, and configuring networks
Attacks that exploit this kind of access
Manage Docker containers, images, networks, and volumes. It is categorised as a Execute tool in the MCP Workspace Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Workspace Server MCP server in PolicyLayer and add a rule for docker_manage: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Workspace Server. Nothing to install.
docker_manage is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the docker_manage rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for docker_manage. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
docker_manage is provided by the MCP Workspace Server MCP server (shayyeffet/ultimate_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →