memory_check_contradiction

Check if a new memory would contradict existing high-importance facts. Call before saving to detect conflicts. Returns contradiction details if found.

Server Mementos @hasna/mementos
Category Read
Risk class Low
Parameters 00 required

What memory_check_contradiction does on Mementos

AI agents call memory_check_contradiction to retrieve information from Mementos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why memory_check_contradiction needs a policy

memory_check_contradiction is a validation/querying tool that reads existing memory facts to perform conflict detection. It has no side effects—it does not create, modify, delete, or execute external operations. The output informs decision-making but does not alter state. While it is part of a memory system alongside write/delete tools (entity_create, entity_delete, bulk_forget), this specific tool is read-only.

From the tool's definition Tool performs a check/query operation ('Check if a new memory would contradict existing high-importance facts') that returns information ('Returns contradiction details if found') without modifying or deleting any data.

Questions about memory_check_contradiction

What does the memory_check_contradiction tool do? +

Check if a new memory would contradict existing high-importance facts. Call before saving to detect conflicts. Returns contradiction details if found. It is categorised as a Read tool in the Mementos MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on memory_check_contradiction? +

Register the Mementos MCP server in PolicyLayer and add a rule for memory_check_contradiction: 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 Mementos. Nothing to install.

What risk level is memory_check_contradiction? +

memory_check_contradiction is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit memory_check_contradiction? +

Yes. Add a rate_limit block to the memory_check_contradiction 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.

How do I block memory_check_contradiction completely? +

Set action: deny in the PolicyLayer policy for memory_check_contradiction. 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.

What MCP server provides memory_check_contradiction? +

memory_check_contradiction is provided by the Mementos MCP server (@hasna/mementos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

memory_check_contradiction is one line of Mementos'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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.