Return the live working-memory view for a session: active task,
AI agents call current_state to retrieve information from State Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays the current state of a coding agent's working memory (active task, context snapshot, etc.) without creating, modifying, deleting, or executing anything. It is a passive inspection mechanism, analogous to 'get' or 'fetch' operations. The low severity reflects minimal blast radius—misuse retrieves information but cannot cause unintended data loss or external operations.
From the tool's definition Tool name 'current_state' and description 'Return the live working-memory view' indicate a retrieval operation with no modification or side effects. The verb 'Return' and phrase 'view for a session' confirm this is a read-only query of existing state.
Attacks that exploit this kind of access
Return the live working-memory view for a session: active task,. It is categorised as a Read tool in the State Trace MCP Server, which means it retrieves data without modifying state.
Register the State Trace MCP server in PolicyLayer and add a rule for current_state: 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 State Trace. Nothing to install.
current_state 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_state 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_state. 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_state is provided by the State Trace MCP server (agent-pattern-labs/state-trace). 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 →