ima-memory-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ima-memory-mcp记住:用户偏好使用 PostgreSQL,重要项目偏好 TypeScript。"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ima-memory-mcp
基于 IMA 笔记 + IMA 知识库的 AI Agent 持久化记忆与跨会话共享 MCP Server。
以 IMA 笔记存储记忆与会话存档
每篇笔记创建后自动关联到 IMA 知识库,实现跨工具共享
纯 MCP 设计,无插件,支持 Kimi Code、OpenCode、Cursor 等任何 MCP 客户端
前置条件
Node.js 18+
一个 IMA OpenAPI 账号及凭证(Client ID + API Key)
在 IMA 客户端中创建一个知识库,用于存放共享记忆
Related MCP server: Synapto
安装
# 1. 从 GitHub 克隆到任意目录
git clone https://github.com/mason-yb-zhang/ima-memory-mcp.git
cd ima-memory-mcp
# 2. 安装依赖
npm install
# 3. 配置 IMA 凭证
mkdir -p ~/.config/ima
echo "your-client-id" > ~/.config/ima/client_id
echo "your-api-key" > ~/.config/ima/api_key
# 4. (可选)指定默认知识库名称或 ID
# 默认会查找名为 Agent-Memory-KB 的知识库;也可直接指定 ID:
echo "your-kb-id" > ~/.config/ima/memory_kb_id
# 5. 注册 MCP server
node scripts/install.mjs然后重启 Kimi Code CLI(或你使用的其他 MCP 客户端)。
凭证获取
访问 https://ima.qq.com/agent-interface 申请 IMA OpenAPI 的 Client ID 和 API Key。
工具列表
记忆管理
add_memory— 保存记忆search_memory— 搜索记忆list_memories— 列出记忆update_memory— 追加更新delete_memory— 标记删除decay_memories— 清理冷短期记忆promote_memory— 升级为长期记忆
会话存档
save_session— 存档会话list_sessions— 列出存档search_session— 搜索会话get_session_detail— 读取会话全文
使用示例
记住:我喜欢用 TypeScript,不要在代码里写冗余注释。
搜索之前关于数据库选型的记忆。
保存当前会话,标题叫"Docker 部署讨论"。存储结构
记忆笔记:IMA 笔记本
Agent-Memories会话存档:IMA 笔记本
Agent-Sessions知识库同步:每篇笔记创建后自动通过
add_knowledge(media_type=11)关联到 IMA 知识库默认知识库名称:
Agent-Memory-KB可通过环境变量
IMA_MEMORY_KB_NAME修改名称可通过环境变量
IMA_MEMORY_KB_ID或文件~/.config/ima/memory_kb_id直接指定知识库 ID
每条记忆 / 每个会话既是一篇 IMA 笔记,也是知识库中的一个条目
跨工具共享
所有接入同一个 ima-memory MCP Server 的 AI 工具(Kimi Code、OpenCode、Cursor 等)读写同一份 IMA 凭证和同一个知识库,因此天然共享同一个记忆空间。
注意事项
由于 IMA OpenAPI 的限制:
不支持真正删除笔记,
delete_memory仅追加[DELETED]标记。不支持替换笔记正文,
update_memory仅追加[UPDATED]标记。标题一旦创建无法修改,因此
promote_memory也只能追加标记。
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
Shared memory for all your AI agents, your whole team and every MCP client — save, search, recall.
Persistent memory for AI agents — log and recall conversation context over MCP.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to maintain persistent memory across sessions by capturing conversations, extracting durable knowledge, and injecting relevant context, supporting various MCP-compatible platforms.12MIT
- AlicenseNot gradedqualityAmaintenanceProvides persistent, searchable memory for MCP-compatible agents, enabling recall by meaning, automatic decay, trust scoring, and cross-agent handoffs.5MIT
- AlicenseNot gradedqualityBmaintenanceCross-vendor AI memory over MCP. Provides a persistent memory store with tools to write, search, list, forget, and supersede memories from any MCP-capable AI client.MIT
- AlicenseAqualityCmaintenanceMCP server providing persistent memory for AI agents, enabling them to read, write, and query memories across sessions.924MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mason-yb-zhang/ima-memory-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server