push
Pushes commits to a remote repository. Returns structured data with success status, remote, branch, summary, and whether the remote branch was newly created.
This record as markdown: /tools/io-github-dave-london-docker/push.md
What push does on Docker
AI agents use push to create or update resources in Docker, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Docker environment.
Why push is rated Medium
Pushing commits modifies the remote repository irreversibly by adding new commits to a branch. However, it is not classified as Destructive because pushes are typically reversible (commits can be reverted, force-pushed, or branches reset), and the primary purpose is to propagate changes rather than delete data.
From the tool's definition Tool description states it 'Pushes commits to a remote repository' and returns data about successful pushes to remote branches. The words 'pushes commits' and 'remote repository' indicate modifying remote state.
Attacks that exploit this kind of access
The rule that runs push safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Docker, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For push, this is the rule to start with:
push stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Docker, apply this rule, and every push call is checked against it from then on.
Questions about push
Pushes commits to a remote repository. Returns structured data with success status, remote, branch, summary, and whether the remote branch was newly created. It is categorised as a Write tool in the Docker MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Docker MCP server in PolicyLayer and add a rule for push: 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 Docker. Nothing to install.
push is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the push 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 push. 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.
push is provided by the Docker MCP server (@paretools/docker). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Docker, and thousands of servers like it.
This server
Across the catalogue