Scan ANY file (code, markdown, text, HTML, config) - structure with condensed code skeletons. USE BEFORE Read. For exploration, pass budget=1500 (or 300 for a quick look) - full depth is rarely needed on the first pass. To READ one function/class/section verbatim afterwards, pass focus=
AI agents call scan_file 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.
scan_file performs static analysis and structure extraction on source code and text files. It returns metadata about code organization (classes, functions, methods, line numbers) without executing code, creating data, modifying files, or deleting anything. The tool is purely informational and read-only, making it a Read category risk with low severity.
From the tool's definition The tool 'scan_file' is described as analyzing file structure and extracting 'classes, functions, methods, and metadata with precise line numbers' for 'codebase exploration.' The description explicitly states 'USE BEFORE Read' and directs users to 'pass…
Attacks that exploit this kind of access
Scan ANY file (code, markdown, text, HTML, config) - structure with condensed code skeletons. USE BEFORE Read. For exploration, pass budget=1500 (or 300 for a quick look) - full depth is rarely needed on the first pass. To READ one function/class/section verbatim afterwards, pass focus=. 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_file: 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_file 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_file 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_file. 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_file 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 →