list_changes
AI agents call list_changes to retrieve information from Git Polite without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or enumerate uncommitted changes in a Git repository. No description is provided, which slightly lowers confidence, but the name and sibling tools (apply_changes, auto_commit, diff) suggest this is a read-only operation that queries repository state rather than modifying it. Misuse carries minimal risk as it only exposes information.
From the tool's definition Tool name 'list_changes' indicates a query/retrieval operation. Within the context of a Git staging/commit organization tool, listing changes would retrieve Git status or diff information without modifying repositories.
Attacks that exploit this kind of access
list_changes. It is categorised as a Read tool in the Git Polite MCP Server, which means it retrieves data without modifying state.
Register the Git Polite MCP server in PolicyLayer and add a rule for list_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.
list_changes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_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 list_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.
list_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 →