Get SafetyCulture inspections for a specific time period using the feed API.
AI agents call get_inspections to retrieve information from SafetyCulture MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves inspection records from the SafetyCulture system for analysis. It performs a query operation that returns existing data with no side effects, reversibility concerns, or capacity to modify, delete, or execute operations. Even though it requires authentication (via sibling 'authenticate' tool), the tool itself only reads data.
From the tool's definition Tool description states 'Get SafetyCulture inspections for a specific time period' — retrieves inspection data without modification or side effects.
Attacks that exploit this kind of access
Get SafetyCulture inspections for a specific time period using the feed API. It is categorised as a Read tool in the SafetyCulture MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SafetyCulture MCP Server MCP server in PolicyLayer and add a rule for get_inspections: 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 SafetyCulture MCP Server. Nothing to install.
get_inspections 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 get_inspections 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 get_inspections. 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.
get_inspections is provided by the SafetyCulture MCP Server MCP server (zerubroberts/safetyculture-mcp-server). 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 →