apply_changes
AI agents use apply_changes 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.
Apply_changes on a Git server performs write operations by modifying the staging area or applying diffs to tracked files. This is reversible (changes can be unstaged or reverted), so it is Write rather than Destructive. Severity is high because an AI agent could inadvertently apply unintended changes to a codebase.
From the tool's definition Tool name is 'apply_changes' on a Git server that 'organizes Git changes into clean, focused commits.' The sibling tools (auto_commit, diff, list_changes, unstack) indicate this server manipulates Git state.
Attacks that exploit this kind of access
apply_changes. 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 apply_changes: 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.
apply_changes 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 apply_changes 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 apply_changes. 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.
apply_changes 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 →