oecd_search_datasets
AI agents call oecd_search_datasets 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.
Based on the server's stated purpose of providing access to public education indicators and the consistent pattern of sibling tools being read-only queries (oecd_list_education_datasets, uis_get_education_data, uis_list_indicators, etc.), this tool almost certainly searches or filters existing datasets without modifying them. The 'search' semantic typically indicates a Read operation.
From the tool's definition Tool name contains 'search_datasets' which aligns with read operations; sibling tools on the server are all Read operations (list, get, compare, benchmark functions querying UNESCO UIS and OECD data).
Attacks that exploit this kind of access
oecd_search_datasets. 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 oecd_search_datasets: 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.
oecd_search_datasets 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 oecd_search_datasets 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 oecd_search_datasets. 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.
oecd_search_datasets 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 →