Get all seats for a specific office
AI agents call get_office_seats to retrieve information from MCP Seat Reservation Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries seat information for an office without creating, modifying, deleting, executing code, or committing financial transactions. It is a straightforward read operation with minimal blast radius if misused by an AI agent—worst case being information disclosure of seat availability.
From the tool's definition Tool name 'get_office_seats' and description 'Get all seats for a specific office' indicate data retrieval with no modification. The description explicitly uses 'Get', a read operation.
Attacks that exploit this kind of access
Get all seats for a specific office. It is categorised as a Read tool in the MCP Seat Reservation Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Seat Reservation Server MCP server in PolicyLayer and add a rule for get_office_seats: 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 MCP Seat Reservation Server. Nothing to install.
get_office_seats 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_office_seats 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_office_seats. 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_office_seats is provided by the MCP Seat Reservation Server MCP server (nomura565/claude-chat-app-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 →