Return recent PHI-safe chat traces for UI display.
AI agents call get_chat_traces to retrieve information from MCPDischarge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical chat data for display purposes only—a read-only operation. While the medium severity reflects that chat traces in a healthcare setting may contain sensitive information and could expose patterns of clinical decision-making or patient interactions if misused by an agent, the tool itself performs no write, execute, destructive, or financial actions.
From the tool's definition Tool name 'get_chat_traces' and description 'Return recent PHI-safe chat traces for UI display' indicate data retrieval with no modification or side effects. The 'PHI-safe' qualifier suggests protective measures are in place.
Attacks that exploit this kind of access
Return recent PHI-safe chat traces for UI display. It is categorised as a Read tool in the MCPDischarge MCP Server, which means it retrieves data without modifying state.
Register the MCPDischarge MCP server in PolicyLayer and add a rule for get_chat_traces: 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 MCPDischarge. Nothing to install.
get_chat_traces 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 get_chat_traces 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 get_chat_traces. 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.
get_chat_traces is provided by the MCPDischarge MCP server (prashantsingh1234/mcp_project). 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 →