analyze_diff

Analyze git diff for change risk assessment and classification Use when native

Server Claude Flow claude-flow
Category Read
Risk class Low
Parameters 00 required

What analyze_diff does on Claude Flow

AI agents call analyze_diff to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why analyze_diff needs a policy

This tool performs static analysis on git diff output to classify changes by risk level. It reads and queries existing diff data to produce insights, with no side effects on the repository or codebase. The incomplete description ('Use when native' appears truncated) does not suggest execution or destructive capabilities.

From the tool's definition Tool analyzes git diff for risk assessment and classification. The verb 'analyze' and the constraint 'for change risk assessment' indicate data retrieval and inspection without modification.

Questions about analyze_diff

What does the analyze_diff tool do? +

Analyze git diff for change risk assessment and classification Use when native. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on analyze_diff? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for analyze_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 Claude Flow. Nothing to install.

What risk level is analyze_diff? +

analyze_diff is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit analyze_diff? +

Yes. Add a rate_limit block to the analyze_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.

How do I block analyze_diff completely? +

Set action: deny in the PolicyLayer policy for analyze_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.

What MCP server provides analyze_diff? +

analyze_diff is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.