AI agents call session_read to retrieve information from It2mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves terminal screen contents without modifying or executing anything. However, the severity is medium rather than low because terminal screen contents may contain sensitive information (passwords, API keys, source code, private data) depending on what was previously executed in that session.
From the tool's definition Tool name is 'session_read' and description states it 'Read[s] the visible screen contents of an iTerm2 session.' The verb 'read' and explicit retrieval operation indicate this is a read-only action with no side effects.
Attacks that exploit this kind of access
Read the visible screen contents of an iTerm2 session. It is categorised as a Read tool in the It2mcp MCP Server, which means it retrieves data without modifying state.
Register the It2 MCP server in PolicyLayer and add a rule for session_read: 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 It2mcp. Nothing to install.
session_read 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_read 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_read. 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_read is provided by the It2 MCP server (urjitbhatia/it2mcp). 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 →