Run artifact_safety_report across every file in a directory and aggregate the findings.
AI agents call scan_directory_tool to retrieve information from Model Safety MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
scan_directory_tool reads file contents and runs analysis reports across a directory structure. This is a query/inspection operation with no side effects—it doesn't modify files, delete data, execute arbitrary commands, or trigger external operations. The underlying operations (artifact_safety_report, modelscan_scan, picklescan_scan) are scanning/inspection tools, not executables.
From the tool's definition The tool 'scans' and 'aggregates findings' across files in a directory. It performs safety auditing operations that read and analyze artifacts without modifying, deleting, or executing code.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Run artifact_safety_report across every file in a directory and aggregate the findings. It is categorised as a Read tool in the Model Safety MCP MCP Server, which means it retrieves data without modifying state.
Register the Model Safety MCP server in PolicyLayer and add a rule for scan_directory_tool: 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 Model Safety MCP. Nothing to install.
scan_directory_tool 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_directory_tool 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_directory_tool. 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_directory_tool is provided by the Model Safety MCP server (itsalissonsilva/modelsafetymcp). 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 →