dead_client_report
AI agents call dead_client_report to retrieve information from ERP-File MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to generate a report on inactive or non-performing clients, which is a read operation that retrieves and aggregates data from the ERP system without modifying it. Severity is medium due to potential sensitivity of business intelligence data (client performance metrics), though no destructive or financial operations are implied.
From the tool's definition Tool name 'dead_client_report' and sibling tools (outstanding_report, sales_report, unbilled_report) suggest data retrieval from ERP/sheet data. No description provided, but naming pattern and server context indicate querying/reporting functionality.
Attacks that exploit this kind of access
dead_client_report. It is categorised as a Read tool in the ERP-File MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ERP-File MCP Server MCP server in PolicyLayer and add a rule for dead_client_report: 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 ERP-File MCP Server. Nothing to install.
dead_client_report 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 dead_client_report 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 dead_client_report. 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.
dead_client_report is provided by the ERP-File MCP Server MCP server (sharpjsdev/mcp-server). 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 →