Structural diff against a git ref - which functions are new/changed/removed since HEAD/main/a release, with condensed skeletons. USE THIS INSTEAD of git diff for review and
AI agents call scan_diff to retrieve information from Scantool - File Scanner MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes existing code structure and changes without modifying, executing, or deleting any data. It provides visibility into code differences through tree-sitter parsing, which is a fundamental read operation. The tool has no side effects beyond returning information for inspection. The blast radius of misuse is minimal—an AI agent cannot cause harm through querying code structure analysis.
From the tool's definition Tool performs structural analysis and comparison ('Structural diff against a git ref') to identify code changes ('which functions are new/changed/removed'). The output is a condensed view ('condensed skeletons') for review purposes.
Attacks that exploit this kind of access
Structural diff against a git ref - which functions are new/changed/removed since HEAD/main/a release, with condensed skeletons. USE THIS INSTEAD of git diff for review and. It is categorised as a Read tool in the Scantool - File Scanner MCP MCP Server, which means it retrieves data without modifying state.
Register the Scantool - File Scanner MCP server in PolicyLayer and add a rule for scan_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 Scantool - File Scanner MCP. Nothing to install.
scan_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 scan_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 scan_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.
scan_diff is provided by the Scantool - File Scanner MCP server (mariusei/file-scanner-mcp). 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 →