AI agents call get_gardens to retrieve information from Golemio without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves public garden information from the Golemio open data API—a read-only query with no side effects, no data modification, no execution of arbitrary code, and no destructive or financial impact. The 'get_' prefix and sibling tool patterns confirm it is a simple data retrieval function.
From the tool's definition Tool name 'get_gardens' follows the 'get_*' pattern consistent with all sibling tools (get_departures, get_parking_lots, get_air_quality_stations, etc.), which are query/retrieval operations on Prague's public open data API.
Attacks that exploit this kind of access
get_gardens. It is categorised as a Read tool in the Golemio MCP Server, which means it retrieves data without modifying state.
Register the Golemio MCP server in PolicyLayer and add a rule for get_gardens: 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 Golemio. Nothing to install.
get_gardens 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_gardens 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_gardens. 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_gardens is provided by the Golemio MCP server (mrmebelman/golemio-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 →