AI agents call get_lot to retrieve information from Raygister without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves construction lot information without side effects. The 'Read-only' server designation and retrieve-focused language ('Retrieve', 'get_') confirm no data is created, modified, deleted, or executed. Blast radius is minimal—querying lot details poses negligible security risk.
From the tool's definition Tool description explicitly states 'Retrieve a single lot' with data fields (description, type, instance number, status, specifications). Server is described as 'Read-only MCP server'. No modification, deletion, or execution capability.
Attacks that exploit this kind of access
Retrieve a single lot with its full description, type, instance number, current status, and inline specifications. Use list_lots first if the lot ID is unknown. It is categorised as a Read tool in the Raygister MCP Server, which means it retrieves data without modifying state.
Register the Raygister MCP server in PolicyLayer and add a rule for get_lot: 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 Raygister. Nothing to install.
get_lot 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_lot 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_lot. 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_lot is provided by the Raygister MCP server (raygisterinc/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 →