Run applicable analyzers against an observable and collect aggregated results with taxonomy summary. Can auto-detect data type. By default only an explicit allowlist of analyzers runs; set fanOut=true to submit to every applicable analyzer (capped by CORTEX_MAX_FANOUT). Fanning out submits the ob...
AI agents invoke cortex_analyze_observable to trigger actions in Cortex. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers external operations by running analyzers and submitting data to third-party services. It is not a simple read — it actively dispatches jobs and causes side effects including quota consumption, potential SSRF-by-proxy, and IOC disclosure. The fan-out mode amplifies the blast radius significantly, making severity high.
From the tool's definition 'Run applicable analyzers against an observable', 'submits the observable to many third-party services (SSRF-by-proxy / IOC disclosure / quota burn)', 'set fanOut=true to submit to every applicable analyzer'
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Run applicable analyzers against an observable and collect aggregated results with taxonomy summary. Can auto-detect data type. By default only an explicit allowlist of analyzers runs; set fanOut=true to submit to every applicable analyzer (capped by CORTEX_MAX_FANOUT). Fanning out submits the observable to many third-party services (SSRF-by-proxy / IOC disclosure / quota burn), so it is opt-in. It is categorised as a Execute tool in the Cortex MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cortex MCP server in PolicyLayer and add a rule for cortex_analyze_observable: 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_analyze_observable is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the cortex_analyze_observable 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_analyze_observable. 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_analyze_observable 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.
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 →