Find conflicting data in the dictionary. If key provided, checks only that entry. If no key, scans recent entries.
AI agents call cortex_check_contradictions to retrieve information from Cortex MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes existing data in a dictionary to identify contradictions. It performs no writes, deletions, or external operations. Even though it's part of a memory/decision system, the function itself is purely informational—reading data and returning analysis results.
From the tool's definition Tool description states it 'find[s] conflicting data' and 'checks' entries—read-only query operations with no modification or deletion. The verb 'checks' and 'scans' indicate inspection/retrieval without side effects.
Attacks that exploit this kind of access
Find conflicting data in the dictionary. If key provided, checks only that entry. If no key, scans recent entries. It is categorised as a Read tool in the Cortex MCP MCP Server, which means it retrieves data without modifying state.
Register the Cortex MCP server in PolicyLayer and add a rule for cortex_check_contradictions: 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_check_contradictions 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_check_contradictions 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_check_contradictions. 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_check_contradictions 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.
cortex_check_contradictions 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 →