Push local changes to a remote repository. Uploads local branch commits to the remote repository, updating remote references.
AI agents use git_push to create or update resources in Git MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Git MCP Server environment.
git_push uploads commits to a remote repository, modifying remote references. While this is a write operation (not locally destructive), it can have significant blast radius by overwriting remote branches, affecting other collaborators, and potentially breaking CI/CD pipelines.
From the tool's definition Push local changes to a remote repository. Uploads local branch commits to the remote repository, updating remote references.
Attacks that exploit this kind of access
Push local changes to a remote repository. Uploads local branch commits to the remote repository, updating remote references. It is categorised as a Write tool in the Git MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Git MCP Server MCP server in PolicyLayer and add a rule for git_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 Git MCP Server. Nothing to install.
git_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 git_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 git_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.
git_push is provided by the Git MCP Server MCP server (wty0512/git-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 →