AI agents call class.industry-resolve 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 performs a lookup/translation of industry classification codes between different standard taxonomies. It retrieves and maps data with no side effects, modifications, or financial transactions. The only concern is the pay-per-call billing model noted in the server description, but the tool itself is a pure read/query operation.
From the tool's definition Cross-walk an industry code across NAICS ↔ SIC ↔ ISIC Rev.4 ↔ NACE Rev.2 (Census + UN concordances)
Attacks that exploit this kind of access
Cross-walk an industry code across NAICS ↔ SIC ↔ ISIC Rev.4 ↔ NACE Rev.2 (Census + UN concordances). 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 class.industry-resolve: 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.
class.industry-resolve 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 class.industry-resolve 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 class.industry-resolve. 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.
class.industry-resolve 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 →