correct
Store corrections to prevent AI mistakes from recurring. Corrections override normal memories and always surface first for accurate responses.
Instructions
Store a correction. Always maximum importance. Always surfaces first.
Use this when the AI made a mistake and you want to prevent it from
happening again. Corrections override normal memories.
Args:
content: What the correct behavior/answer should be.
context: When/where this correction applies.
tags: Comma-separated tags.
namespace: Namespace for organizing memories.Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | ||
| context | No | ||
| tags | No | ||
| namespace | No | default |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Implementation Reference
- neveronce/server.py:73-91 (handler)The `correct` tool handler which uses the Memory layer to store corrections.
@mcp.tool() def correct(content: str, context: str = "", tags: str = "", namespace: str = "default") -> str: """Store a correction. Always maximum importance. Always surfaces first. Use this when the AI made a mistake and you want to prevent it from happening again. Corrections override normal memories. Args: content: What the correct behavior/answer should be. context: When/where this correction applies. tags: Comma-separated tags. namespace: Namespace for organizing memories. """ mem = _get_mem() tag_list = [t.strip() for t in tags.split(",") if t.strip()] if tags else [] mid = mem.correct(content, context=context, tags=tag_list, namespace=namespace) return f"Stored correction #{mid} (importance: 10, always surfaces first)"