Pushes a local branch from the active repository to the remote (origin).
AI agents use git_push_branch to create or update resources in Git PR MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Git PR MCP Server environment.
Pushing a branch to a remote repository is a write operation that creates or updates a remote branch. It is reversible (the branch can be deleted or reset), so it does not qualify as Destructive. However, misuse could expose unintended code or overwrite remote branches, giving it medium severity.
From the tool's definition Pushes a local branch from the active repository to the remote (origin)
Attacks that exploit this kind of access
Pushes a local branch from the active repository to the remote (origin). It is categorised as a Write tool in the Git PR MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Git PR MCP Server MCP server in PolicyLayer and add a rule for git_push_branch: 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 Git PR MCP Server. Nothing to install.
git_push_branch 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 git_push_branch 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 git_push_branch. 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.
git_push_branch is provided by the Git PR MCP Server MCP server (peterj/git-pr-mcp). 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 →