Mark a file as created/done in file tree. Saves checkpoint if file exists on disk.
AI agents use cortex_tick_file 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.
This tool writes metadata or checkpoint state about files rather than creating, deleting, or executing arbitrary operations. It modifies the internal state of the memory/tracking system (marking completion status and saving checkpoints), which is a write operation.
From the tool's definition Tool marks files as "created/done" and "saves checkpoint if file exists on disk." These are reversible state modifications—the checkpoint can be overwritten or the marking removed.
Attacks that exploit this kind of access
Mark a file as created/done in file tree. Saves checkpoint if file exists 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_tick_file: 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_tick_file 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_tick_file 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_tick_file. 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_tick_file 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 →