AI agents call entire_session_info to retrieve information from Entire without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a purely informational tool that retrieves and displays session metadata. It has no side effects—it does not modify, delete, execute, or move anything. The blast radius of misuse is minimal; an agent could access session information it shouldn't see (a confidentiality concern), but cannot cause lasting damage or state changes. This fits the Read category with low severity.
From the tool's definition The tool "Show details for a specific session ID including transcript path, files touched, and token usage" performs only retrieval and inspection operations.
Attacks that exploit this kind of access
Show details for a specific session ID including transcript path, files touched, and token usage. Uses \. It is categorised as a Read tool in the Entire MCP Server, which means it retrieves data without modifying state.
Register the Entire MCP server in PolicyLayer and add a rule for entire_session_info: 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 Entire. Nothing to install.
entire_session_info 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 entire_session_info 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 entire_session_info. 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.
entire_session_info is provided by the Entire MCP server (jurislm/entire-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 →