Get compressed project state (under 200 tokens) — call before every action. Includes token budget warning if >50% used.
AI agents call cortex_get_state to retrieve information from Cortex MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns current system state information. It performs no writes, deletions, code execution, or financial operations. The recommendation to 'call before every action' confirms it is designed as a safe, informational read-only operation. The low severity reflects minimal blast radius if misused by an AI agent — querying state cannot directly harm systems or data.
From the tool's definition Tool description explicitly states it 'Get[s] compressed project state' and 'Includes token budget warning' — purely a retrieval/query operation with no side effects or modifications.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Get compressed project state (under 200 tokens) — call before every action. Includes token budget warning if >50% used. It is categorised as a Read tool in the Cortex MCP MCP Server, which means it retrieves data without modifying state.
Register the Cortex MCP server in PolicyLayer and add a rule for cortex_get_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 Cortex MCP. Nothing to install.
cortex_get_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 cortex_get_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 cortex_get_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.
cortex_get_state is provided by the Cortex MCP server (neuralnexustech/cortex-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 →