mem9 MCP Server
Enables AI assistants to manage memories via the mem9 memory service, supporting memory storage, semantic search, retrieval, update, and deletion across multiple platforms.
README
@mem9/mcp-server
Universal MCP Server for mem9 memory service. One server, all platforms.
Quick Start
# Requires a running mnemo-server and API key
git clone https://github.com/you06/mem9-mcp.git
cd mem9-mcp
npm install
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
MEM9_API_KEY |
Yes | - | API key for authentication (also serves as tenant ID) |
MEM9_API_URL |
No | https://api.mem9.ai |
mnemo-server base URL |
MEM9_AGENT_ID |
No | auto-detected | Agent identifier |
MEM9_LOG_LEVEL |
No | info |
Log level: debug, info, warn, error |
MEM9_TIMEOUT_MS |
No | 10000 |
HTTP request timeout (ms) |
MEM9_SEARCH_LIMIT |
No | 10 |
Default search result limit |
Agent ID is auto-detected from platform environment variables (CURSOR_WORKSPACE, CLAUDE_CODE_VERSION, CODEX_CLI_VERSION).
Tools
| Tool | Description |
|---|---|
memory_store |
Store a new memory (processed via fact extraction) |
memory_search |
Search memories by semantic similarity and keywords |
memory_get |
Retrieve a specific memory by ID |
memory_update |
Update an existing memory (direct field update) |
memory_delete |
Delete a memory |
Development
npm install
npm run build
npm test
Local Testing with Claude Code / Codex
Before publishing, you can test the MCP server locally by pointing to the built entry file:
Claude Code:
claude mcp add mem9 -e MEM9_API_KEY=your-key -e MEM9_API_URL=http://localhost:8080 -- node /path/to/mem9-mcp/dist/index.js
Or in .mcp.json:
{
"mcpServers": {
"mem9": {
"command": "node",
"args": ["/path/to/mem9-mcp/dist/index.js"],
"env": {
"MEM9_API_URL": "http://localhost:8080",
"MEM9_API_KEY": "your-key"
}
}
}
}
Codex:
codex mcp add mem9 -- node /path/to/mem9-mcp/dist/index.js
Or in .codex/config.toml:
[mcp_servers.mem9]
command = "node"
args = ["/path/to/mem9-mcp/dist/index.js"]
[mcp_servers.mem9.env]
MEM9_API_URL = "http://localhost:8080"
MEM9_API_KEY = "your-key"
After code changes, run npm run build and restart the MCP client to pick up the new build.
Platform Setup
Cursor
Settings > Features > MCP Servers:
{
"mcpServers": {
"mem9": {
"command": "npx",
"args": ["-y", "@mem9/mcp-server"],
"env": {
"MEM9_API_URL": "http://localhost:8080",
"MEM9_API_KEY": "your-key"
}
}
}
}
Claude Code
claude mcp add mem9 -- npx -y @mem9/mcp-server
Or in .mcp.json:
{
"mcpServers": {
"mem9": {
"command": "npx",
"args": ["-y", "@mem9/mcp-server"],
"env": {
"MEM9_API_URL": "http://localhost:8080",
"MEM9_API_KEY": "your-key"
}
}
}
}
OpenAI Codex
codex mcp add mem9 -- npx -y @mem9/mcp-server
Or in .codex/config.toml:
[mcp_servers.mem9]
command = "npx"
args = ["-y", "@mem9/mcp-server"]
[mcp_servers.mem9.env]
MEM9_API_URL = "http://localhost:8080"
MEM9_API_KEY = "your-key"
License
Apache-2.0
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。