AI agents call current_tasks 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 retrieves debugging state information (processes and threads) from a Pernosco trace without modifying, executing, or deleting anything. It is purely informational, analogous to listing or querying data. The blast radius of misuse is minimal — an agent could only observe the trace context, not alter execution or access external systems.
From the tool's definition Tool description states 'Get active processes and threads at the current focus moment' — a retrieval operation with no side effects. The verb 'Get' and the query-like nature align with read-only debugging introspection.
Attacks that exploit this kind of access
Get active processes and threads at the current focus moment. 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 current_tasks: 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.
current_tasks 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 current_tasks 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 current_tasks. 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.
current_tasks 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 →