This record as markdown: /tools/io-github-dave-london-npm/rebase.md
What rebase does on Npm
AI agents invoke rebase 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 rebase is rated High
A git rebase rewrites commit history by replaying commits on top of a new base, which is an irreversible history-modifying operation. While it can be aborted mid-way, once completed and pushed, it rewrites history. It triggers external git operations with significant side effects (commit rewriting, potential force-push requirements).
From the tool's definition Rebases the current branch onto a target branch. Supports abort, continue, skip, and quit for conflict resolution.
Attacks that exploit this kind of access
The rule that runs rebase 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 rebase, this is the rule to start with:
rebase 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 rebase call is checked against it from then on.
Questions about rebase
Rebases the current branch onto a target branch. Supports abort, continue, skip, and quit for conflict resolution. Returns structured data with success status, branch info, conflicts, and rebased commit count. 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 rebase: 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.
rebase 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 rebase 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 rebase. 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.
rebase 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