Push current branch to origin
AI agents invoke fleet_git_push to trigger actions in Fleet. 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.
Pushing to a remote Git repository is an external operation with significant side effects: it modifies the remote repository state, can trigger CI/CD pipelines, and in a production deployment context (as described for this Fleet server) could initiate automated deployments. While reversible in theory (force-revert), the downstream effects on production systems make this high severity.
From the tool's definition Push current branch to origin
Documented attack patterns abuse exactly the kind of access fleet_git_push gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fleet, and nothing reaches the server without passing your rules. This is the rule we recommend for fleet_git_push:
{
"version": "1",
"default": "deny",
"tools": {
"fleet_git_push": {
"limits": [
{
"counter": "fleet_git_push_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} fleet_git_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.
Push current branch to origin. It is categorised as a Execute tool in the Fleet MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Fleet MCP server in PolicyLayer and add a rule for fleet_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 Fleet. Nothing to install.
fleet_git_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 fleet_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 fleet_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.
fleet_git_push is provided by the Fleet MCP server (wrxck/fleet). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Fleet, 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.
39 Fleet tools catalogued and risk-classified — across an index of 43,000+ MCP servers.