Return the full ordered MCP tool call trace for a patient's workflow.
AI agents call trace_workflow 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 an audit log or trace of past MCP calls for a patient's discharge workflow. It performs a read-only query operation returning ordered historical data without creating, modifying, deleting, executing code, or committing financial actions. The return of workflow history is a standard audit/logging function.
From the tool's definition Tool name 'trace_workflow' and description 'Return the full ordered MCP tool call trace for a patient's workflow' indicate retrieval and querying of historical workflow data with no modifications or side effects.
Attacks that exploit this kind of access
Return the full ordered MCP tool call trace for a patient's workflow. 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 trace_workflow: 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.
trace_workflow 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 trace_workflow 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 trace_workflow. 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.
trace_workflow 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 →