Time-series of monthly wages by NACE sector and education level.
AI agents call get_wage_data to retrieve information from LUSTAT Wages MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves historical wage statistics for analysis purposes. There are no side effects, data modification, destructive actions, code execution, or financial transactions involved. The blast radius of misuse is minimal—an agent could only access already-published wage data, not alter it or trigger external operations.
From the tool's definition Tool retrieves "Time-series of monthly wages data by NACE sector and education level" with no indication of modification, deletion, or external operations.
Attacks that exploit this kind of access
Time-series of monthly wages by NACE sector and education level. It is categorised as a Read tool in the LUSTAT Wages MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LUSTAT Wages MCP Server MCP server in PolicyLayer and add a rule for get_wage_data: 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 LUSTAT Wages MCP Server. Nothing to install.
get_wage_data 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 get_wage_data 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 get_wage_data. 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.
get_wage_data is provided by the LUSTAT Wages MCP Server MCP server (poseidon73561/lustattest-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 →