AI agents call git_diff to retrieve information from Git without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
git_diff retrieves and displays differences between Git objects (working tree, staging area, or repository refs). It produces no side effects, creates no commits, modifies no data, and executes no external operations. This is a pure read operation with minimal risk if misused by an AI agent—the worst outcome is exposure of repository contents already accessible to the agent.
From the tool's definition Tool name 'git_diff' and description 'Show unstaged, staged, or ref-to-ref diff' indicate retrieval of version differences without modification or deletion. The verb 'Show' confirms a read-only operation.
Attacks that exploit this kind of access
Show unstaged, staged, or ref-to-ref diff. Supports optional LLM-oriented filtering. It is categorised as a Read tool in the Git MCP Server, which means it retrieves data without modifying state.
Register the Git MCP server in PolicyLayer and add a rule for git_diff: 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. Nothing to install.
git_diff 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 git_diff 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 git_diff. 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.
git_diff is provided by the Git MCP server (selfagency/git-mcp). 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 →