memory_mcp

View on GitHub

一键启动 memory mcp ，对外提供sse服务

3 stars PythonServers & Infrastructure Updated Aug 9, 2025

mcpmcp-server

Documentation

Memory MCP 服务器

> 基于 MCP Servers - memory 改造的知识图谱管理服务器

功能特点

支持多种启动方式：交互式、命令行、JSON配置
生成符合知识图谱知识背景的短故事（实验）（查看 `mcp_client.py` 中的 `handle_sampling_message` 函数）
完整的知识图谱管理功能
支持MCP协议:tools、resource、sampling
自动数据持久化
灵活的配置选项

快速开始

启动方式

1. 交互式启动

直接运行程序（双击），按提示输入配置：

程序会提示输入端口号（默认8080）
程序会提示输入内存文件路径（默认为程序所在目录的memory.json）

2. 命令行传参

启动服务

bash

mcp_server_memory.exe --port 8080 --memory-path ./memory.json

3. JSON配置启动

通过管道传入JSON配置：

bash

echo '{"jsonrpc": "2.0","method": "start","id": 2,"params":{"port": 8080, "memory_path": "./memory.json"}}' | ./mcp_server_memory.exe

获取帮助信息

bash

echo '{"jsonrpc": "2.0","method": "help","id": 1}' | mcp_server_memory.exe

配置项

参数	说明	默认值
port	服务器监听端口	8080
memory_path	数据存储文件路径	./memory.json

API 接口

实体操作

`create_entities`: 创建实体
`delete_entities`: 删除实体
`search_nodes`: 搜索节点
`open_nodes`: 打开指定节点

关系操作

`create_relations`: 创建关系
`delete_relations`: 删除关系

观察操作

`add_observations`: 添加观察
`delete_observations`: 删除观察

图谱操作

`read_graph`: 读取完整图谱

Resource 接口

`memory://short-story/all`: 获取所有基于知识图谱生成的短故事
`memory://short-story/{topic}`: 获取指定主题的短故事
- `topic`: 故事主题关键词，例如 "科技"、"历史" 等

数据持久化

数据以JSON行格式存储
自动保存最新配置到 `config.json`
支持相对/绝对路径
自动创建不存在的目录

注意事项

Windows系统推荐使用 `\` 或 `\\` 作为路径分隔符
确保程序对存储路径有读写权限
首次运行自动创建存储文件

Frequently asked questions

What is memory_mcp?

memory_mcp is 一键启动 memory mcp ，对外提供sse服务

How do I install memory_mcp?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is memory_mcp open source?

Yes — it is hosted on GitHub at https://github.com/shadowcz007/memory_mcp and has 3 stars.

Related MCP tools

mcp-neo4j

Model Context Protocol with Neo4j Python-based implementation. Trusted by 700+ developers. Trusted by 700+ developers. Trusted by 700+ developers.

789 Python

databasemcpmcp-server+2

gpt-researcher

An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations. Built for the Model Context Protocol to

24,026 Python

agentaiautomation+8

fastapi_mcp

Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth! Python-based implementation. Trusted by 11000+ developers.

11,002 Python

aiauthenticationauthorization+10

mcp

AWS MCP Servers — helping you get the most out of AWS, wherever you use MCP. Python-based implementation. Trusted by 6900+ developers.

6,922 Python

awsmcpmcp-client+6

ida-pro-mcp

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP. Python-based implementation. Trusted by 4100+ developers.

4,123 Python

aiaiagentbinary-analysis+6