Memory MCP Server

@drdee

代码仓库

基本信息

分类

记忆与知识

许可证

MIT

传输方式

stdio

作者

drdee

关于 Memory MCP Server

An mcp server that you can use to store and retrieve ideas, prompt templates, personal preferences to use with you favourite AI tool that supports the modelcontextprovider protocol.

Memory MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "memory-mcp": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "memory-mcp"
      ]
    }
  }
}

Memory MCP Server 工具

Store a new memory with a title and content

Retrieve a specific memory by ID or title

List all stored memories

Update an existing memory

Delete a memory

概览

What is Memory MCP?

Memory MCP is a Model Context Protocol server for storing and retrieving memories using a low-level server implementation and SQLite storage. It is designed for developers who want to add persistent memory capabilities to MCP-compatible agents or applications.

How to use Memory MCP?

Install the package via uv pip install memory-mcp (or from source with uv pip install .). Run the server by executing the memory-mcp command. For debugging, use the MCP Inspect CLI tool to list, call, and inspect tools.

Key features of Memory MCP

Five CRUD tools: remember, get_memory, list_memories, update_memory, delete_memory
Persistent storage backed by SQLite
Debug and inspect via mcp inspect with debug mode
Dependency management with uv for fast, reliable resolution
Lightweight implementation using the Model Context Protocol

Use cases of Memory MCP

Storing and recalling meeting notes or project updates
Building a personal memory database for chatbot assistants
Prototyping memory-backed AI agents with MCP tool integration
Providing long-term context for conversational applications

常见问题

How do I install Memory MCP?

Install using `uv pip install memory-mcp`. If you don't have `uv`, follow the official installation instructions at https://github.com/astral-sh/uv#installation.

How do I run the server?

Run `memory-mcp` in your terminal. This starts the MCP server that exposes the five memory tools.

What tools are available?

The server provides `remember`, `get_memory`, `list_memories`, `update_memory`, and `delete_memory`. Each has specific parameters; use `mcp inspect` to see their schemas.

How can I debug the server?

Use the MCP Inspect CLI tool (`mcp inspect`) after installing `mcp[cli]` via `uv pip install mcp[cli]`. Connect to the running server and use commands like `tools`, `call`, and `debug on`.

How do I update dependencies?

This project uses a `uv.lock` file. Run `uv pip compile pyproject.toml -o uv.lock` to regenerate it after changing dependencies.

记忆与知识分类下的更多 MCP 服务器

Tempreon

Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

HandbookHub MCP

veryayskiy

Search saved employee handbooks from your AI assistant. Four read-only tools list authorized handbooks, browse policies, search content, and read source pages with citation links. Uses scoped bearer tokens and Streamable

PLUR

plur-ai

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

226

agentleFS

One permissioned folder your team and your AI agents both log into.

Groundwork

Rarefied-Earth

Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.