AI agents call diff to retrieve information from Python without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and returns diff statistics and optionally patch content. It has no side effects, does not modify files, execute code, or delete data. It is purely informational—a read operation used for viewing differences between files or versions.
From the tool's definition Returns file-level diff statistics as structured data. Use full=true for patch content. The tool retrieves and queries diff information without modifying or executing any code.
Attacks that exploit this kind of access
Returns file-level diff statistics as structured data. Use full=true for patch content. It is categorised as a Read tool in the Python MCP Server, which means it retrieves data without modifying state.
Register the Python MCP server in PolicyLayer and add a rule for 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 Python. Nothing to install.
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 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 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.
diff is provided by the Python MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
diff is one line of Python's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →