AI agents call cortex_get_job_artifacts to retrieve information from Cortex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves artifacts/data from an already-completed analysis job. It performs a read-only query operation with no side effects, no data modification, no code execution, and no destructive actions. The blast radius of misuse is minimal — an attacker could view analysis results they might not be authorized to see, but cannot alter or delete data. This is a standard Read category classification.
From the tool's definition Tool name is 'cortex_get_job_artifacts' and description states it 'Get artifacts (extracted observables/IOCs) from a completed analysis job' — uses the verb 'Get' which indicates retrieval of data without modification or side effects.
Attacks that exploit this kind of access
Get artifacts (extracted observables/IOCs) from a completed analysis job. It is categorised as a Read tool in the Cortex MCP Server, which means it retrieves data without modifying state.
Register the Cortex MCP server in PolicyLayer and add a rule for cortex_get_job_artifacts: 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. Nothing to install.
cortex_get_job_artifacts 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_job_artifacts 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_job_artifacts. 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_job_artifacts is provided by the Cortex MCP server (solomonneas/cortex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
cortex_get_job_artifacts is one line of Cortex's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →