Return recent tool calls, RBAC violations, and alerts for the UI.
AI agents call get_recent_calls 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 audit/logging data and system alerts for display purposes. It performs no mutations, execution of code, financial transactions, or destructive actions. While it accesses sensitive information (RBAC violations, alerts), the read-only nature and audit/compliance context (serving the UI for monitoring) classify it as Read.
From the tool's definition Tool description states 'Return recent tool calls, RBAC violations, and alerts for the UI' — retrieval and querying of logged events without modification or side effects.
Attacks that exploit this kind of access
Return recent tool calls, RBAC violations, and alerts for the UI. 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_recent_calls: 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_recent_calls 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_recent_calls 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_recent_calls. 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_recent_calls 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 →