uis_list_versions
AI agents call uis_list_versions to retrieve information from Pypi:global Education without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the naming convention and context of the education data server, this tool almost certainly lists available versions of UNESCO UIS datasets or similar versioned resources. This is a read-only query operation with no side effects, no state modification, and no destructive capability. The empty description lowers confidence slightly, but the semantic evidence from tool name and sibling tools is strong.
From the tool's definition Tool name 'uis_list_versions' with no description provided, but semantic pattern indicates a listing/enumeration operation consistent with read-only data retrieval.
Attacks that exploit this kind of access
uis_list_versions. It is categorised as a Read tool in the Pypi:global Education MCP Server, which means it retrieves data without modifying state.
Register the Pypi:global Education MCP server in PolicyLayer and add a rule for uis_list_versions: 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:global Education. Nothing to install.
uis_list_versions 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 uis_list_versions 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 uis_list_versions. 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.
uis_list_versions is provided by the Pypi:global Education MCP server (pypi:global-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 →