Graph Memory RAG MCP Server

@lecharles

代码仓库

基本信息

分类

记忆与知识

传输方式

stdio

作者

lecharles

关于 Graph Memory RAG MCP Server

A Model Context Protocol (MCP) server implementation for graph-based memory storage with RAG capabilities

#graph-memory#mcp-server#memory-storage

Graph Memory RAG 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": {
    "graph-memory-rag-mcp-server": {
      "command": "node",
      "args": [
        "app.js"
      ]
    }
  }
}

Graph Memory RAG MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Graph Memory RCP MCP Server?

Graph Memory RCP MCP Server is a Model Context Protocol (MCP) server that provides graph-based memory storage. It allows AI agents to store and retrieve information in a graph structure, maintaining context and relationships between pieces of information. It is intended for developers integrating graph memory into AI agent workflows.

How to use Graph Memory RCP MCP Server?

Install dependencies with npm install and start the server with node app.js. The server exposes tools for creating entities and relationships, querying entities and relationships by type, and deleting entities with cascading relationship cleanup.

Key features of Graph Memory RCP MCP Server

In-memory graph database storage
Entity creation and management
Relationship creation between entities
Query capabilities for entities and relationships
Delete operations with cascading relationship cleanup
MCP-compliant interface

Use cases of Graph Memory RCP MCP Server

AI agents maintaining persistent context across conversations
Storing and retrieving structured knowledge with entity-relationship links
Managing dynamic memory graphs where nodes and edges can be added or removed
Experimenting with graph-based memory in MCP‑enabled applications

常见问题

What dependencies does Graph Memory RCP MCP Server require?

It requires `@modelcontextprotocol/sdk: ^1.0.3` and `zod: ^3.22.4`.

How is data stored in Graph Memory RCP MCP Server?

Data is stored entirely in‑memory using two maps: one for entities and one for relationships. There is no persistent storage.

What operations can I perform with the server’s tools?

You can create entities (with name, type, and observations), create relationships between entities, query entities and relationships by type, and delete entities (which also removes their associated relationships).

Does Graph Memory RCP MCP Server use authentication or transport layers?

The README does not describe any authentication or transport configuration; it uses the standard MCP interface.

What are the limits of the in‑memory storage?

The README does not specify explicit limits. Since storage is in‑memory, capacity is bounded by available system memory and data is lost when the server stops.

记忆与知识分类下的更多 MCP 服务器

Context7 MCP - Up-to-date Docs For Any Cursor Prompt

upstash

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

58.7K

Tempreon

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

Takibi Base

Deian Isac

Ask your Takibi Base collections anything; get answers with cited passages and a support score.

The Cloud

Teka

The Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your

OpenLore

aakarim

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab