AI agents call get_medical_institutions 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 city infrastructure data (medical institutions in Prague) with no side effects, no data modification, no code execution, and no financial impact. It is a simple data query operation consistent with other public transit and city data endpoints on the same server.
From the tool's definition Tool name is 'get_medical_institutions' and is part of a Golemio open data API server that queries Prague's public city data. The 'get_' prefix and sibling tools (get_air_quality_stations, get_departures, get_parking_lots, etc.) are all read-only queries.
Attacks that exploit this kind of access
get_medical_institutions. 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_medical_institutions: 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_medical_institutions 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_medical_institutions 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_medical_institutions. 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_medical_institutions 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 →