rozvrh
AI agents call rozvrh to retrieve information from Bakaláři MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the server's stated purpose of retrieving (not modifying) educational data and the context of sibling tools being read-only queries, rozvrh most likely retrieves a student or classroom schedule. This is a read-only data retrieval operation with no side effects. Confidence is moderate due to empty tool description, but context is clear.
From the tool's definition Tool name 'rozvrh' (Czech for 'schedule') is part of a server that 'provides access to... retrieve schedules, permanent timetables, absence records, and grades.' Sibling tools (absence, staly_rozvrh, znamky) are all read operations on student data.
Attacks that exploit this kind of access
rozvrh. It is categorised as a Read tool in the Bakaláři MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Bakaláři MCP Server MCP server in PolicyLayer and add a rule for rozvrh: 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 Bakaláři MCP Server. Nothing to install.
rozvrh 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 rozvrh 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 rozvrh. 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.
rozvrh is provided by the Bakaláři MCP Server MCP server (mirecekd/bakalari-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 →