preview_changes
Preview all changes before committing
This record as markdown: /tools/agentics-ai-code-mcp/preview-changes.md
What preview_changes does on Code MCP Server
AI agents call preview_changes to retrieve information from Code MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why preview_changes is rated Low
The tool previews changes before they are committed, which is a read-only operation — it retrieves and displays pending changes without applying, writing, or executing anything. This is analogous to a 'git diff' or dry-run view. Confidence is slightly reduced because the description is brief and doesn't explicitly confirm no side effects.
From the tool's definition Preview all changes before committing
Attacks that exploit this kind of access
The rule that runs preview_changes safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Code MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For preview_changes, this is the rule to start with:
preview_changes is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Code MCP Server, apply this rule, and every preview_changes call is checked against it from then on.
Questions about preview_changes
Preview all changes before committing. It is categorised as a Read tool in the Code MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Code MCP Server MCP server in PolicyLayer and add a rule for preview_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 MCP Server. Nothing to install.
preview_changes 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 preview_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.
Set action: deny in the PolicyLayer policy for preview_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.
preview_changes is provided by the Code MCP Server MCP server (agentics-ai/code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Code MCP Server, and thousands of servers like it.
This server
Across the catalogue