unstack
AI agents use unstack to create or update resources in Git Polite — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Git Polite environment.
Given the context of a Git commit organization tool with 'apply_changes' and 'auto_commit' peers, 'unstack' most likely performs a write operation that modifies Git history or staging state. While theoretically reversible via 'git reflog' or undoing, the primary effect is to create or modify Git commits/branches, placing it in Write rather than Destructive. Without explicit description, confidence is moderate (0.6).
From the tool's definition Tool 'unstack' is a sibling to 'apply_changes', 'auto_commit', 'diff', and 'list_changes' in a Git workflow server. The name 'unstack' suggests reversing or splitting commit stacks, which would modify Git state (commit history, branch state).
Attacks that exploit this kind of access
unstack. It is categorised as a Write tool in the Git Polite MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Git Polite MCP server in PolicyLayer and add a rule for unstack: 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 Git Polite. Nothing to install.
unstack 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 unstack 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 unstack. 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.
unstack is provided by the Git Polite MCP server (uneco/mcp-git-polite). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →