AI agents call occupation.search 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 an occupational database and returns information without side effects. It performs a passive lookup against O*NET data, matching the Read category (search, list, get, fetch). The low severity reflects that misuse would only expose occupational reference data with no destructive, financial, or system impact.
From the tool's definition Tool description states 'Find O*NET occupations by keyword' and 'Returns ranked occupations' — purely a search/retrieval operation with no modification, deletion, or external execution described.
Attacks that exploit this kind of access
Find O*NET occupations by keyword (job title, skill, or activity). Returns ranked occupations with SOC/O*NET-SOC code + title. The. 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 occupation.search: 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.
occupation.search 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 occupation.search 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 occupation.search. 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.
occupation.search 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 →