store
Store AI memories with tags, context, importance levels, and namespaces for persistent organization and retrieval in the NeverOnce MCP server.
Instructions
Store a memory.
Args:
content: The memory content to store.
tags: Comma-separated tags (e.g. "preference,ui,dark-mode").
context: When/where this memory applies.
importance: 1-10, how important this memory is.
namespace: Namespace for organizing memories.Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | ||
| tags | No | ||
| context | No | ||
| importance | No | ||
| namespace | No | default |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Implementation Reference
- neveronce/server.py:54-70 (handler)The 'store' MCP tool definition and handler implementation in neveronce/server.py, which uses the Memory object to store data.
@mcp.tool() def store(content: str, tags: str = "", context: str = "", importance: int = 5, namespace: str = "default") -> str: """Store a memory. Args: content: The memory content to store. tags: Comma-separated tags (e.g. "preference,ui,dark-mode"). context: When/where this memory applies. importance: 1-10, how important this memory is. 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.store(content, tags=tag_list, context=context, importance=importance, namespace=namespace) return f"Stored memory #{mid}"