Search US colleges + universities via the Department of Education College Scorecard. Filter by name, IPEDS id, state/city/zip, ownership (1=Public | 2=Private nonprofit | 3=Private for-profit), predominant degree (0..4), enrollment range. Returns curated identity + admissions + cost + aid + compl...
AI agents call edu.college-scorecard to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns educational institution metadata from a public government database. It retrieves information based on filter parameters but does not create, modify, delete, or execute any operations. No financial transactions occur (despite the server supporting USDC settlements, this specific tool merely reads data).
From the tool's definition Tool performs 'Search' and 'Filter' operations on College Scorecard data; 'Returns curated identity + admissions + cost + aid + completion + earnings + repayment fields per school' — data retrieval only with no side effects.
Attacks that exploit this kind of access
Search US colleges + universities via the Department of Education College Scorecard. Filter by name, IPEDS id, state/city/zip, ownership (1=Public | 2=Private nonprofit | 3=Private for-profit), predominant degree (0..4), enrollment range. Returns curated identity + admissions + cost + aid + completion + earnings + repayment fields per school. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for edu.college-scorecard: 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 Mcp. Nothing to install.
edu.college-scorecard 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 edu.college-scorecard 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 edu.college-scorecard. 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.
edu.college-scorecard is provided by the MCP server (@2sio/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 →