Search Secretary of State / DFI business registrations via OpenCorporates (sourced directly from official state registries; data lineage is auditable). Use to map a trade name to its legal entity, identify the registered agent for service of process, find related entities under common ownership, ...
AI agents call business_entity_search to retrieve information from DOL WHD MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries publicly available business entity information from official state registries with no side effects. The operations are purely informational lookups to obtain existing data about legal entities, making it a Read-category tool with low severity since misuse would only expose publicly available information.
From the tool's definition Tool performs 'Search' of business registrations and 'identify', 'find', 'confirm' operations against public state registry data via OpenCorporates.
Attacks that exploit this kind of access
Search Secretary of State / DFI business registrations via OpenCorporates (sourced directly from official state registries; data lineage is auditable). Use to map a trade name to its legal entity, identify the registered agent for service of process, find related entities under common ownership, or confirm an establishment is an active legal entity. Free tier is ~50 lookups/day with attribution; higher volume requires an OPENCORPORATES_API_KEY env var. For US states, pass the two-letter state code (MI, IL, etc.) as. It is categorised as a Read tool in the DOL WHD MCP MCP Server, which means it retrieves data without modifying state.
Register the DOL WHD MCP server in PolicyLayer and add a rule for business_entity_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 DOL WHD MCP. Nothing to install.
business_entity_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 business_entity_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 business_entity_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.
business_entity_search is provided by the DOL WHD MCP server (uhq-actual/dol_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 →