AI agents use memory_contradictions to create or update resources in Exocortex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Exocortex environment.
While the tool can read/list contradictions (Read), its primary value and risk comes from resolving or dismissing contradictions between memories, which modifies the memory store. Resolution may overwrite or invalidate existing memory entries. This is a Write-level action; severity is medium because incorrect resolution by an AI agent could corrupt persistent memory state, though it appears reversible in principle.
From the tool's definition 'resolve detected contradictions between memories' and 'can be dismissed or resolved inline'
Attacks that exploit this kind of access
List or resolve detected contradictions between memories. Contradictions are detected nightly and can be dismissed or resolved inline. It is categorised as a Write tool in the Exocortex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Exocortex MCP server in PolicyLayer and add a rule for memory_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 Exocortex. Nothing to install.
memory_contradictions 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 memory_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 memory_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.
memory_contradictions is provided by the Exocortex MCP server (shawnhack/exocortex). 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 →