Pushes commits to a remote repository. Returns structured data with success status, remote, branch, summary, and whether the remote branch was newly created.
AI agents invoke push to trigger actions in Http. 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.
This tool triggers an external Git push operation to a remote repository, which has significant side effects: it modifies a remote repository's state, potentially overwrites remote branches, and creates new remote branches. While not purely destructive (commits aren't deleted), it's an external operation that can cause irreversible changes to shared remote state (e.g., pushing broken code, overwriting others' work).
From the tool's definition Pushes commits to a remote repository... whether the remote branch was newly created
Documented attack patterns abuse exactly the kind of access push gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Http, and nothing reaches the server without passing your rules. This is the rule we recommend for push:
{
"version": "1",
"default": "deny",
"tools": {
"push": {
"limits": [
{
"counter": "push_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}push stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
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 Execute tool in the Http MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Http 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 Http. Nothing to install.
push 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 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 Http MCP server (@paretools/http). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Http, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
202 Http tools catalogued and risk-classified — across an index of 43,000+ MCP servers.