Assess company domain trust and risk signals.
AI agents call check_company_domain to retrieve information from RecruiterCheck MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs domain reputation analysis and risk assessment, which are fundamentally read operations. It gathers and reports on trust indicators and potential fraud signals associated with a domain, similar to checking a WHOIS record or running a domain through a reputation service. There is no mutation of data, code execution on user systems, destructive capability, or financial impact.
From the tool's definition Tool description states it "Assess[es] company domain trust and risk signals" — this is a query/analysis operation that retrieves or evaluates existing information about a domain without modifying, executing code, deleting data, or moving money.
Attacks that exploit this kind of access
Assess company domain trust and risk signals. It is categorised as a Read tool in the RecruiterCheck MCP MCP Server, which means it retrieves data without modifying state.
Register the RecruiterCheck MCP server in PolicyLayer and add a rule for check_company_domain: 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 RecruiterCheck MCP. Nothing to install.
check_company_domain 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 check_company_domain 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 check_company_domain. 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.
check_company_domain is provided by the RecruiterCheck MCP server (jesslbrown/recruitercheck-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 →