AI agents call business.id-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 only looks up and returns company legal entity information (identifiers, jurisdiction, canonical name) from external registries (SEC, GLEIF). There are no write, execute, destructive, or financial side effects. Severity is low as the worst-case misuse is retrieving publicly available company data.
From the tool's definition 'Company legal-entity resolver: give one of name, lei, cik, or ticker → LEI, CIK, ticker(s), jurisdiction, canonical name' — purely resolves and retrieves company identity data from SEC and GLEIF.
Attacks that exploit this kind of access
Company legal-entity resolver: give one of name, lei, cik, or ticker → LEI, CIK, ticker(s), jurisdiction, canonical name (SEC + GLEIF). 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 business.id-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.
business.id-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 business.id-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 business.id-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.
business.id-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 →