Compress current session to summary, save to DB and .cortex/snapshots/ on disk
AI agents use cortex_save_snapshot to create or update resources in Cortex MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cortex MCP environment.
cortex_save_snapshot creates and modifies data by compressing session state and persisting it to both database and filesystem. This is a write operation (create/store), not destructive (no deletion) or irreversible in the destructive sense.
From the tool's definition Tool description states 'save to DB and .cortex/snapshots/ on disk' — explicitly performs write operations that create/store data persistently.
Attacks that exploit this kind of access
Compress current session to summary, save to DB and .cortex/snapshots/ on disk. It is categorised as a Write tool in the Cortex MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cortex MCP server in PolicyLayer and add a rule for cortex_save_snapshot: 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_save_snapshot is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cortex_save_snapshot 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_save_snapshot. 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_save_snapshot 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 →