AI agents call session_report to retrieve information from Iris MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays historical data (conversation history) without side effects. It is a read-only operation that queries existing session data. The verb 'View' explicitly indicates data retrieval rather than creation, modification, or deletion. No code execution, financial transactions, or destructive operations are involved.
From the tool's definition Tool name 'session_report' combined with description 'View the conversation history for a session' indicates a retrieval operation with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
View the conversation history for a session. It is categorised as a Read tool in the Iris MCP MCP Server, which means it retrieves data without modifying state.
Register the Iris MCP server in PolicyLayer and add a rule for session_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 Iris MCP. Nothing to install.
session_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 session_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 session_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.
session_report is provided by the Iris MCP server (jenova-marie/iris-mcp). 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 →