Onboard an app to GitHub: create repo, push code, protect branches
AI agents use fleet_git_onboard to create or update resources in Fleet — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fleet environment.
The tool creates new repositories, pushes code, and configures branch protections on GitHub. While repository creation and code pushes are reversible (repos can be deleted, commits can be reverted), they are substantive Write operations that establish application infrastructure. Branch protection configurations persist until explicitly changed.
From the tool's definition Tool performs 'create repo, push code, protect branches' — these are reversible but significant modifications to Git/GitHub infrastructure that establish long-term state (repository creation, branch protection rules).
Documented attack patterns abuse exactly the kind of access fleet_git_onboard 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_onboard:
{
"version": "1",
"default": "deny",
"tools": {
"fleet_git_onboard": {
"limits": [
{
"counter": "fleet_git_onboard_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}fleet_git_onboard 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.
Free to start. No card required.
Onboard an app to GitHub: create repo, push code, protect branches. It is categorised as a Write tool in the Fleet MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fleet MCP server in PolicyLayer and add a rule for fleet_git_onboard: 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_onboard 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 fleet_git_onboard 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_onboard. 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_onboard 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.