AI agents call property_dossier to retrieve information from CorteX402 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Property dossier tools typically aggregate and retrieve property-related data (ownership, history, lien records, etc.) without modifying data. While the empty description prevents absolute certainty, the sibling tools are all clearly informational queries, and the pay-per-call settlement model suggests these are data retrieval services rather than write or destructive operations.
From the tool's definition Tool name 'property_dossier' in the context of a data products server alongside 'sanctions_screen', 'aviation_weather', 'mortgage_rates', 'title_chain', and 'wallet_balance' suggests it retrieves pre-computed or queried property information.
Attacks that exploit this kind of access
property_dossier. It is categorised as a Read tool in the CorteX402 MCP Server, which means it retrieves data without modifying state.
Register the CorteX402 MCP server in PolicyLayer and add a rule for property_dossier: 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 CorteX402. Nothing to install.
property_dossier 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 property_dossier 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 property_dossier. 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.
property_dossier is provided by the CorteX402 MCP server (ooak21/cortex402-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 →