Return total MCP tool call counts, optionally filtered by patient.
AI agents call get_mcp_call_count 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 statistics from audit logs or call tracking systems without creating, modifying, deleting, or executing external operations. Even though it accesses hospital data, the operation is purely informational (a 'get' operation) and carries minimal risk if misused by an AI agent — at worst, an attacker gains visibility into call patterns, which is a confidentiality concern rather than integrity or…
From the tool's definition Tool name is 'get_mcp_call_count' and description states it 'Return[s] total MCP tool call counts' — a retrieval operation with no modification or side effects. The optional filtering 'by patient' indicates querying existing audit/logging data.
Attacks that exploit this kind of access
Return total MCP tool call counts, optionally filtered by patient. 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_mcp_call_count: 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_mcp_call_count 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_mcp_call_count 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_mcp_call_count. 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_mcp_call_count 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 →