AI agents invoke devbox_git to trigger actions in Homelab. 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 executes git commands, which are external operations with side effects that depend on their arguments. While git operations are generally not destructive, they are Execute-class because they run external commands that modify system state.
From the tool's definition Tool description states it can "Run git status, pull, log, or clone" - these are operations that execute external commands (git commands) whose effects depend on arguments and can modify local state (pull, clone).
Attacks that exploit this kind of access
Run git status, pull, log, or clone on the devbox. It is categorised as a Execute tool in the Homelab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Homelab MCP server in PolicyLayer and add a rule for devbox_git: 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 Homelab. Nothing to install.
devbox_git 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 devbox_git 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 devbox_git. 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.
devbox_git is provided by the Homelab MCP server (nainounen/homelab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
devbox_git is one line of Homelab's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →