AI agents invoke git_operation to trigger actions in Code. 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.
While git operations can range from read-only (log, status) to destructive (force-push, reset --hard), the tool permits execution of git commands whose effects depend entirely on arguments provided by the AI agent. This is classic Execute category behavior—triggering external operations with argument-dependent consequences.
From the tool's definition Tool is described as 'Execute a git operation in the project repository' and exists alongside tools that 'run terminal commands' and 'manage git'. Git operations can include arbitrary commands with side effects (rebasing, force-pushing, resetting, bisecting).
Documented attack patterns abuse exactly the kind of access git_operation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Code, and nothing reaches the server without passing your rules. This is the rule we recommend for git_operation:
{
"version": "1",
"default": "deny",
"tools": {
"git_operation": {
"limits": [
{
"counter": "git_operation_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}git_operation 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.
Execute a git operation in the project repository. It is categorised as a Execute tool in the Code MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Code MCP server in PolicyLayer and add a rule for git_operation: 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 Code. Nothing to install.
git_operation 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 git_operation 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_operation. 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_operation is provided by the Code MCP server (54yyyu/code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Code tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 Code tools catalogued and risk-classified — across an index of 42,500+ MCP servers.