【读取会话】当用户说
AI agents call read_session to retrieve information from MCP Session Saver without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries existing AI conversation records stored as Markdown files. It has no side effects and does not modify, delete, or execute operations. It is clearly a Read operation that simply fetches stored session data for viewing/access purposes.
From the tool's definition Tool name is 'read_session' and the description indicates it retrieves conversation records. The sibling tools include 'save_session', 'search_sessions', and 'delete_session', which confirms this is part of a session management system where read_session…
Attacks that exploit this kind of access
【读取会话】当用户说. It is categorised as a Read tool in the MCP Session Saver MCP Server, which means it retrieves data without modifying state.
Register the MCP Session Saver MCP server in PolicyLayer and add a rule for read_session: 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 MCP Session Saver. Nothing to install.
read_session 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 read_session 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 read_session. 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.
read_session is provided by the MCP Session Saver MCP server (oscar-wang-xin/mcp-session-saver). 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 →