Validate a tool call before execution (SSRF, command injection, path traversal)
AI agents call scan_tool_call to retrieve information from ZugaShield 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 metadata about a proposed tool call to assess security risks, but does not execute the call, modify data, or trigger external operations. It is a safety gate that performs read-only scanning and analysis, making it a Read category tool. Severity is low because the tool itself only produces security assessments and does not expose dangerous functionality—it prevents it.
From the tool's definition Tool performs validation and scanning of tool calls before execution (SSRF, command injection, path traversal detection). The verb 'Validate' and the focus on detection/checking indicates inspection without side effects.
Attacks that exploit this kind of access
Validate a tool call before execution (SSRF, command injection, path traversal). It is categorised as a Read tool in the ZugaShield MCP Server, which means it retrieves data without modifying state.
Register the ZugaShield MCP server in PolicyLayer and add a rule for scan_tool_call: 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 ZugaShield. Nothing to install.
scan_tool_call 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_tool_call 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_tool_call. 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_tool_call is provided by the ZugaShield MCP server (zuga-technologies/zugashield). 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 →