AST-aligned chunks affected by the diff at ref. Use INSTEAD
AI agents call explain_diff to retrieve information from Code Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and explains code differences without modifying any code or executing operations. It provides contextual information about changes (likely for code review or understanding purposes) with no side effects. This is purely a Read operation—retrieving and analyzing existing diff data. Low severity because misuse only exposes information without operational risk.
From the tool's definition Tool retrieves and analyzes code changes using AST (Abstract Syntax Tree) alignment to show 'chunks affected by the diff'.
Attacks that exploit this kind of access
AST-aligned chunks affected by the diff at ref. Use INSTEAD. It is categorised as a Read tool in the Code Context MCP Server, which means it retrieves data without modifying state.
Register the Code Context MCP server in PolicyLayer and add a rule for explain_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 Code Context. Nothing to install.
explain_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 explain_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 explain_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.
explain_diff is provided by the Code Context MCP server (nachogeinfor-ops/code-context). 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 →