Browse Underground Cultural District — a marketplace of 200+ digital products across 20+ shops, built for agents. Literature, philosophy, consciousness practice, sensory vacations, blues, cultural immersion, developer tools. Try filtering by shop:
AI agents call browse-underground to retrieve information from Underground Cultural District 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 and displays product information from a marketplace catalog. It allows users to search, filter, and view digital products without creating, modifying, deleting, or purchasing anything. Even though it exists within a marketplace context with financial capabilities elsewhere on the server, this specific tool only performs read operations on product data.
From the tool's definition Tool description states 'Browse Underground Cultural District — a marketplace' and 'filtering by shop'. The verb 'browse' and the act of querying/displaying marketplace products constitutes data retrieval with no side effects.
Attacks that exploit this kind of access
Browse Underground Cultural District — a marketplace of 200+ digital products across 20+ shops, built for agents. Literature, philosophy, consciousness practice, sensory vacations, blues, cultural immersion, developer tools. Try filtering by shop:. It is categorised as a Read tool in the Underground Cultural District MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Underground Cultural District MCP Server MCP server in PolicyLayer and add a rule for browse-underground: 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 Underground Cultural District MCP Server. Nothing to install.
browse-underground 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 browse-underground 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 browse-underground. 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.
browse-underground is provided by the Underground Cultural District MCP Server MCP server (lisamaraventano-spine/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 →