Same door for humans and AI. No gatekeeper.Register →
Explorer/MCP/jhongjun1981/MemoryMCP
REMOTE

MemoryMCP

jhongjun1981/MemoryMCP

通用AI记忆服务 - 让任何AI拥有持久记忆能力

8 tools available ↓
The Journeyman
A reasonable amount of history and nothing concerning in the scan.
Time indexed (7mo)
8toolsRemote/ HTTP7moindexed
100% uptime · 406ms avgChecked Oct 4, 2026
Quality Score
57/95
Established
Risk Score
0/100
Clean
▸How is this calculated?
Quality Breakdown
Tenure14.6/20
211 days indexed
Capability16.9/25
Tools: 4.9/13 (8 tools)
Description: 5/5 ✓
Endpoint: 7/7 ✓
Adoption0/25
Use count: 0/20 (0 uses)
Multi-registry: 0/5 (1 registry)
Reliability25/25
Currently live: 10/10 ✓
Uptime history: 15/15 100% (38/38 checks)
Security scan: 0 pts in v1.0; ready to weight when coverage improves
Incomplete Data Cap (60)
Usage data is not available for this server. Quality is capped until adoption can be measured.
Risk
0— Clean
No signals detected.
The scanner shows
8 tools. Nothing caught our attention.
First indexed Mar 18, 2026
Server Profile
⚙
Tools catalogued
8
8 tools available. Full list below.
☁
Hosting
Remote / HTTP
Runs on the internet. No access to your filesystem, SSH keys, or environment variables.
○
Registry presence
Not verified
Not yet verified by the Official MCP Registry.
●
Liveness
100%
Based on 48 checks. Average response: 406ms.
Publisher Verification
Not yet verified by the Official MCP Registry.
Endpoint
https://memorymcp--jhongjun1981.run.tools
Tools (8)
save_memory
保存一条新记忆到持久存储。如果同名记忆已存在则自动更新。 保存前建议先用 search_memories 检查是否已有类似记忆,避免重复。 Args: name: 记忆标题,简洁明确,如"用户偏好-中文交流"、"反馈-不要mock数据库" content: 记忆正文,支持 Markdown。feedback 类型务必包含 Why 和 How to apply type: 记忆类型 - user(用户信息)/feedback(反馈纠正,最重要)/project(项目上下文)/reference(外部资源)/custom(自定义) description: 一句话描述,用于快速检索 namespace: 命名空间,用于项目隔离,默认 "default" tags: 标签,逗号分隔,如 "python,重要,配置"
get_memory
获取一条记忆的完整内容。 Args: id: 记忆 ID(id 和 name 二选一) name: 记忆标题(精确匹配) namespace: 命名空间,默认 "default"
search_memories
搜索记忆(全文搜索,支持中英文)。 Args: query: 搜索关键词 type: 按类型过滤 - user/feedback/project/reference/custom namespace: 按命名空间过滤 tags: 按标签过滤,逗号分隔 limit: 返回条数,默认 20
update_memory
更新一条已有记忆。 Args: id: 记忆 ID(id 和 name 二选一定位记忆) name: 记忆标题(精确匹配定位) namespace: 命名空间,默认 "default" new_name: 新标题(可选) content: 新正文(可选) description: 新描述(可选) tags: 新标签,逗号分隔(可选) type: 新类型(可选)
delete_memory
删除一条记忆(软删除,可恢复)。 Args: id: 记忆 ID(id 和 name 二选一) name: 记忆标题(精确匹配) namespace: 命名空间,默认 "default"
list_memories
列出记忆(摘要模式,不含正文内容)。 Args: type: 按类型过滤 - user/feedback/project/reference/custom namespace: 按命名空间过滤 limit: 返回条数,默认 50 offset: 分页偏移
Show all 8 tools ↓
recall
[重要] 智能回忆 - 你必须在每次新对话的第一轮回复前调用此工具(不传 topic),获取用户信息和历史上下文。 这是你的持久记忆系统,不调用就等于失忆。 必须调用的场景: 1. 每次新对话开始时(不传 topic)→ 获取用户身份、反馈规则、项目上下文 2. 用户提到"之前"、"上次"、"记得吗"时 → 传入相关关键词搜索 3. 开始新任务前 → 搜索是否有相关的反馈或项目记忆 4. 用户问"你还记得..."时 → 必须搜索 不传 topic 返回全部记忆概览;传 topic 搜索相关记忆并返回完整内容。 Args: topic: 回忆主题/关键词(为空则返回全部概览) namespace: 命名空间过滤
smart_note
[重要] 智能笔记 - 当用户说了值得记住的内容时,立即调用此工具自动保存。 此工具会自动判断记忆类型(用户信息/反馈/项目/参考资源),你不需要手动分类。 必须调用的场景: 1. 用户纠正你的做法时("不要..."、"应该..."、"别...")→ 立即调用,这是最重要的记忆 2. 用户透露个人信息时("我是..."、"我负责..."、"我喜欢...")→ 立即调用 3. 用户提到项目决策或截止日期时 → 立即调用 4. 用户提到外部链接或资源位置时 → 立即调用 5. 用户说"记住这个"或类似表达时 → 立即调用 Args: message: 用户原始消息或你总结的要点 namespace: 命名空间,默认 "default"

Is this your server?

Create a free RNWY account to connect your on-chain identity to this server. MCP server claiming is coming; register now and you'll be first in line.

Create your account →
More from jhongjun1981
JHJ-email-mcp
AI-powered email assistant MCP server. Features: send emails, manage SMTP accounts, auto-classify emails with AI, smart auto-reply, contact management, email search and analysis. Supports multiple AI models (Claude, DeepSeek, Zhipu GLM, Qwen).
TaobaoScraper MCP Server
An MCP server for scraping product data from Taobao/Tmall and JD.com, providing 8 tools for scraping, task management, notifications, and system control.
EmailAssistant MCP Server
AI-powered email assistant that enables sending, parsing, and managing emails using natural language. Provides 4 tools (smart_email, parse_email_intent, send_email, email_chat) with SSE/stdio transport support.
Similar servers
sprite-ai
LexIA Pro (EDIVIA)
MCP foncier & urbanisme officiels francais (cadastre, PLU, DVF). LexIA Pro, EDIVIA. Abonnement.
there-there
ai.autoblocks/contextlayer-mcp
Personal context management for AI assistants
Akebono MCP
Provides scored and reasoned Kyoto temple data optimized for AI travel agents to deliver personalized recommendations based on natural language queries. It enables agents to retrieve detailed temple information including historical significance, pricing, and crowd levels.
ai.superfact/superfact
Turn any AI chat or agent run into a beautiful, shareable public page.
Indexed from Smithery · Updates nightlyView on Smithery →