AI agents call session_status to retrieve information from Pernosco without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the current debugger session state to determine what is being inspected. It retrieves read-only debugging metadata (position in execution trace) with no capability to modify, delete, or execute operations. The blast radius of misuse is minimal - an agent could at worst query focus position repeatedly, which has no destructive or operational impact. Classified as Read with low severity.
From the tool's definition Tool description states 'Get current focus position (event number, source file, line)' - purely retrieves current state information without modification or side effects
Attacks that exploit this kind of access
Get current focus position (event number, source file, line) for the connected session. It is categorised as a Read tool in the Pernosco MCP Server, which means it retrieves data without modifying state.
Register the Pernosco MCP server in PolicyLayer and add a rule for session_status: 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 Pernosco. Nothing to install.
session_status 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_status 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_status. 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_status is provided by the Pernosco MCP server (jnjaeschke/pernosco-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 →