GLOBAL: List recent Claude Code sessions from ANY project.
AI agents call sessions_list to retrieve information from Mcp Sessions without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists existing session data without modifying, deleting, or executing anything. It has a read-only profile. Severity is low because listing session metadata poses minimal risk; the blast radius of misuse is confined to exposure of conversation history the user may already have access to, not destructive or financial harm.
From the tool's definition Tool name is 'sessions_list' and description states 'List recent Claude Code sessions' — this is a retrieval/query operation with no side effects.
Attacks that exploit this kind of access
GLOBAL: List recent Claude Code sessions from ANY project. It is categorised as a Read tool in the Mcp Sessions MCP Server, which means it retrieves data without modifying state.
Register the Mcp Sessions MCP server in PolicyLayer and add a rule for sessions_list: 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 Sessions. Nothing to install.
sessions_list 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 sessions_list 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 sessions_list. 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.
sessions_list is provided by the Mcp Sessions MCP server (yurich-ru/mcp-sessions). 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 →