Resolve relationships between datasets (employee-company, customer-employee, etc.)
AI agents call resolve_cross_reference to retrieve information from OrgFlow MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Resolving cross-references is a read/query operation that traverses relationships between datasets (e.g., employee-company, customer-employee) to return linked records. There is no indication it creates, modifies, deletes, or executes anything. Severity is low as misuse would at most expose relational data.
From the tool's definition "Resolve relationships between datasets" — this describes looking up and returning relational/reference data between datasets, with no indication of modification or side effects.
Attacks that exploit this kind of access
Resolve relationships between datasets (employee-company, customer-employee, etc.). It is categorised as a Read tool in the OrgFlow MCP MCP Server, which means it retrieves data without modifying state.
Register the OrgFlow MCP server in PolicyLayer and add a rule for resolve_cross_reference: 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 OrgFlow MCP. Nothing to install.
resolve_cross_reference 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 resolve_cross_reference 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 resolve_cross_reference. 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.
resolve_cross_reference is provided by the OrgFlow MCP server (sujalpat1810/orgflow_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 →