Add a test linked to a feature
AI agents use cortex_add_test 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 creates or stores a test entry in the system's persistent memory/brain, which is a reversible write operation. It does not execute tests, delete data, or trigger external operations. The blast radius is minimal—the worst case is an unnecessary test record being created or a malformed link, both of which can be undone.
From the tool's definition Tool name contains 'add' and description states 'Add a test linked to a feature', indicating creation of a new test record with a link to an existing feature.
Attacks that exploit this kind of access
Add a test linked to a feature. 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_add_test: 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_add_test 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_add_test 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_add_test. 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_add_test 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 →