claude-memory-mcp
An MCP server that gives Claude Code cross-session memory persisted to a plain .claude-memory.md file in your repo.
README
claude-memory-mcp
An MCP server that gives Claude Code cross-session memory — persisted to a plain .claude-memory.md file inside your repo.
Each project gets its own memory. Commit the file to git and it follows the codebase forever.
Install
# Via uvx (no install needed)
uvx claude-memory-mcp
# Or pip
pip install claude-memory-mcp
Configure Claude Code
Add to your project's .mcp.json (or ~/.claude.json for global):
{
"mcpServers": {
"memory": {
"command": "uvx",
"args": ["claude-memory-mcp"]
}
}
}
Tools
| Tool | Description |
|---|---|
memory_read(key) |
Read a stored value |
memory_write(key, value) |
Write a value |
memory_list() |
List all keys |
How it works
Memory is stored as ## sections in .claude-memory.md at your repo root:
# Claude Memory
## architecture-decisions
We use SQLite for local dev and Postgres in prod.
Decided 2025-01-15 — migration too risky mid-sprint.
## current-sprint-context
Working on payment webhook handler. Stripe sends events
to /api/webhooks/stripe. See stripe_handler.py:42.
- Project-scoped: different repos = different memory files
- Git-tracked: commit
.claude-memory.md— memory persists across machines and teammates - Human-readable: open the file, edit it, diff it like any other source file
- No auth, no cloud, no database: just a file
Use cases
- Remember architectural decisions across sessions
- Store "where I left off" context so Claude doesn't ask again
- Share team conventions without repeating them in every prompt
- Track ongoing debugging context across long refactors
Show HN post
Show HN: I built an MCP server that gives Claude Code a persistent memory file
The problem: every Claude Code session starts fresh. I keep explaining the same architectural decisions, the same "don't touch X" rules, the same "we use Y for Z" conventions.
This MCP server persists memory to
.claude-memory.md— a plain markdown file in your repo. Claude reads and writes it across sessions. Commit it to git and it follows the codebase.Three tools:
memory_read,memory_write,memory_list. That's it.Install: add 8 lines to your
.mcp.json, runuvx claude-memory-mcp.
License
MIT
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。