review_changes

Get all changes captured in the task branch for garbage review.

Server Code Intelligence MCP Server tech-spoke/llm-helper
Category Read
Risk class Low
Parameters 00 required

What review_changes does on Code Intelligence MCP Server

AI agents call review_changes to retrieve information from Code Intelligence MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why review_changes needs a policy

This tool retrieves and displays changes that were already made, functioning as a read-only inspection/audit mechanism. No data is created, modified, deleted, or executed. The context of a code intelligence server confirms this is a passive introspection operation designed to review prior modifications before committing them. This presents minimal risk as it only surfaces information.

From the tool's definition Tool description states 'Get all changes captured in the task branch for garbage review' — the verb 'Get' indicates retrieval of data with no side effects. The tool queries existing changes without modifying, deleting, or executing any operations.

Questions about review_changes

What does the review_changes tool do? +

Get all changes captured in the task branch for garbage review. It is categorised as a Read tool in the Code Intelligence MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on review_changes? +

Register the Code Intelligence MCP Server MCP server in PolicyLayer and add a rule for review_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 Code Intelligence MCP Server. Nothing to install.

What risk level is review_changes? +

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

Can I rate-limit review_changes? +

Yes. Add a rate_limit block to the review_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.

How do I block review_changes completely? +

Set action: deny in the PolicyLayer policy for review_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.

What MCP server provides review_changes? +

review_changes is provided by the Code Intelligence MCP Server MCP server (tech-spoke/llm-helper). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.