scan_directory_tool

Run artifact_safety_report across every file in a directory and aggregate the findings.

Server Model Safety MCP itsalissonsilva/modelsafetymcp
Category Read
Risk class Low
Parameters 00 required

What scan_directory_tool does on Model Safety MCP

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.

Why scan_directory_tool needs a policy

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

Questions about scan_directory_tool

What does the scan_directory_tool tool do? +

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.

How do I enforce a policy on scan_directory_tool? +

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.

What risk level is scan_directory_tool? +

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

Can I rate-limit scan_directory_tool? +

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.

How do I block scan_directory_tool completely? +

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.

What MCP server provides scan_directory_tool? +

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.

// 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.