Neurodivergent Memory
未认领A TypeScript-based MCP server implementing a memory system inspired by neurodivergent cognitive styles. It organizes thoughts into five districts (knowledge domains), ranks search results using BM25 semantic ranking, and stores memories as a persistent knowledge graph with bidirectional connections.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'neurodivergent-memory' -- 'npx' '-y' 'neurodivergent-memory@latest' 'init-agent-kit'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多Search & Web服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
17 个工具中显示 17 个
文档中列出的工具 (17)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
connect_memories
Add an edge between two memory nodes
delete_memory
Remove a memory and all its connections
distill_memory
Translate an emotionalprocessing memory into a structured logical artifact
import_memories
Bulk import from inline entries or a snapshot file with dry-run and migration controls
list_memories
Paginated enumeration of all stored memories
memory_stats
Totals, per-district/per-project counts, most-accessed, and orphans
prepare_memory_city_context
Tool mirror of explorememorycity for prompt-limited clients
prepare_packetized_synthesis_context
Tool mirror of synthesizememorypackets for attachment-constrained clients
prepare_synthesis_context
Tool mirror of synthesizememories for prompt-limited clients
register_district
Register a custom district with LUCA ancestry validation
related_to
Hop-proximity + BM25 blend for a given memory ID, with optional goal-context boost
retrieve_memory
Fetch one memory by ID
search_memories
BM25-ranked search with optional context, recencyweight, minscore, district, tag, valence, and intensity filters
storage_diagnostics
Resolved snapshot path, WAL path, and effective persistence source
store_memory
Create a new memory node
traverse_from
BFS graph walk from a node up to N hops
update_memory
Modify content, tags, district, valence, or intensity