zh_edu_mittelschulen
AI agents call zh_edu_mittelschulen to retrieve information from Pypi:zh Education without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to retrieve middle school data from Zurich education statistics (BISTA), consistent with other read-only statistical query tools on this server. Without an explicit description, confidence is moderate, but the context strongly suggests this is a Read operation with minimal blast radius if misused—it only exposes educational statistics.
From the tool's definition Tool name 'zh_edu_mittelschulen' (middle schools) and server context describe querying education statistics. Sibling tools are all read-only queries (list, overview, trend, profile, quote functions).
Attacks that exploit this kind of access
zh_edu_mittelschulen. It is categorised as a Read tool in the Pypi:zh Education MCP Server, which means it retrieves data without modifying state.
Register the Pypi:zh Education MCP server in PolicyLayer and add a rule for zh_edu_mittelschulen: 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 Pypi:zh Education. Nothing to install.
zh_edu_mittelschulen 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 zh_edu_mittelschulen 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 zh_edu_mittelschulen. 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.
zh_edu_mittelschulen is provided by the Pypi:zh Education MCP server (malkreide/zh-education-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 →