MemAura Qoder MCP
MemAura Qoder MCP
把 MemAura/OmniMemory 接入 Qoder CN 的独立适配器。它不会修改或依赖原来的 DeepSeek Harness 项目 /Users/azhai/memaura-mcp-server。
功能
MCP:
store_memory、search_memory、search_memory_hybridHook:每次提交问题前自动混合召回;回答结束后自动保存本轮问答
记忆设备号可配置:默认
qoder-agent,也可改成与其他客户端共享的设备号
Related MCP server: LedgerMem MCP Server
1. 安装依赖
git clone https://github.com/Omnimemory/omnin-Qoder-mcp.git
cd omnin-Qoder-mcp
./install.shinstall.sh 会创建本项目的 .venv,不会修改系统 Python。
2. 配置本地环境
cp .env.example .env编辑 .env,至少填写:
MEMAURA_API_KEY=你的真实APIKey
MEMAURA_DEFAULT_DEVICE_NO=qoder-agent.env 已被 .gitignore 忽略。不要把 API Key 提交到 GitHub。
如果要和 DeepSeek Harness 共用记忆,把设备号改为它使用的值,例如 dsh-agent;使用 qoder-agent 则记忆隔离。
3. 配置 Qoder MCP
在 Qoder 的“设置 → MCP 服务”中打开 mcp.json,使用绝对路径配置:
{
"mcpServers": {
"memaura": {
"type": "stdio",
"command": "/绝对路径/omnin-Qoder-mcp/.venv/bin/python",
"args": ["/绝对路径/omnin-Qoder-mcp/mcp_server.py"],
"env": {
"MEMAURA_API_KEY": "你的真实APIKey",
"MEMAURA_DEFAULT_DEVICE_NO": "qoder-agent",
"MEMAURA_DEFAULT_TOP_K": "10",
"MEMAURA_TIMEOUT": "30"
}
}
}
}把两个“绝对路径”替换为本机实际路径。保存并完全重启 Qoder。MCP 页面应显示三个工具。
4. 启用自动召回和保存
Qoder 的 MCP 配置不会自动触发工具。Hook 配置位于 hooks/hooks.json。将下面的 hooks 配置合并到 ~/.lingma/settings.json(不要覆盖你已有的其他设置):
{
"hooks": {
"UserPromptSubmit": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "/绝对路径/omnin-Qoder-mcp/hooks/run-memory-hook.sh",
"timeout": 25
}]
}],
"Stop": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "/绝对路径/omnin-Qoder-mcp/hooks/run-memory-hook.sh",
"timeout": 25,
"async": true
}]
}]
}
}本项目的 Hook 会自动读取同目录 .env,因此不需要依赖 launchctl。修改后完全退出并重新打开 Qoder。
5. 验证
先验证 Hook 能读取配置:
printf '%s' '{"hook_event_name":"UserPromptSubmit","session_id":"test-001","prompt":"测试记忆 QODER-HOOK-918273"}' | hooks/run-memory-hook.sh再在 Qoder 新建对话:
我刚刚购买了一台测试设备,序列号是 DEVICE-XK-591。等待 30–60 秒,新建另一个对话并问:
我刚刚购买的测试设备序列号是什么?如果能回答 DEVICE-XK-591,说明跨对话保存和召回均生效。
发布插件包
插件包必须是 ZIP,且 ZIP 根目录直接包含 .qoder-plugin/plugin.json。不要把 .venv、.env 或 API Key 放进压缩包:
zip -qr memaura-qoder.zip . \
-x './.venv/*' './.env' './**/__pycache__/*' './*.pyc'在 Qoder“插件 → 导入”中选择生成的 ZIP,而不是选择源码文件夹。安装后仍需按上面的步骤配置本机 Python 环境和 API Key。
故障排查
MCP 能看到工具但不自动保存:Hook 没加载,检查
~/.lingma/settings.json并重启 Qoder。Hook 输出
MEMAURA_API_KEY 未设置:确认项目根目录有.env,并且变量名拼写正确。手动
store_memory成功、自动测试失败:MCP 正常,问题只在 Hook 配置或 Hook 环境。保存成功后不能立即检索:MemAura 入队后通常需要 30–60 秒建立索引。
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 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

LedgerMem MCP Serverofficial
AlicenseNot gradedqualityBmaintenanceEnables persistent memory storage and retrieval for MCP clients, allowing AI assistants to remember facts and context across conversations.10MIT- FlicenseNot gradedqualityCmaintenanceEnables automatic memory retrieval and injection for AI conversations to provide continuous learning through semantic search and memory management.
- FlicenseAqualityDmaintenanceEnables AI assistants to manage memories via the mem9 memory service, supporting memory storage, semantic search, retrieval, update, and deletion across multiple platforms.5
Related MCP Connectors
Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.
An MCP memory server. One memory your agents share — across models, devices and apps.
Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).
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/Omnimemory/omnin-Qoder-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server