This record as markdown: /tools/io-github-dave-london-npm/checkout.md
What checkout does on Npm
AI agents invoke checkout to trigger actions in Npm. 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.
Why checkout is rated High
This tool switches git branches or restores working tree files, which triggers external git operations that change repository state. While not permanently destructive, switching branches or restoring files can overwrite uncommitted changes and alter the working environment in ways that are hard to reverse (e.g., discarding local modifications).
From the tool's definition Switches branches or restores files... detached HEAD status... whether a new branch was created
Attacks that exploit this kind of access
The rule that runs checkout safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Npm, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For checkout, this is the rule to start with:
checkout 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Npm, apply this rule, and every checkout call is checked against it from then on.
Questions about checkout
Switches branches or restores files. Returns structured data with ref, previous ref, whether a new branch was created, and detached HEAD status. Pass. It is categorised as a Execute tool in the Npm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Npm MCP server in PolicyLayer and add a rule for checkout: 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 Npm. Nothing to install.
checkout 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 checkout 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 checkout. 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.
checkout is provided by the Npm MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Npm, and thousands of servers like it.
This server
Across the catalogue