mcpField
G
Graph Memory RAG MCP Server

Graph Memory RAG MCP Server

Local
github.com/lecharlesMemory & Knowledge0Updated 77w ago
Repository

About Graph Memory RAG MCP Server

Graph Memory RAG MCP Server is an in-memory graph-based memory service for AI agents. It supports creating, querying, and deleting entities and their relationships.

Key features

  1. 01Store graph data in memory
  2. 02Create and manage entities
  3. 03Link entities with relationships
  4. 04Query entities and relationships by type
  5. 05Delete entities and clean up linked relationships

Use cases

  1. 01Store information with explicit connections
  2. 02Retrieve graph memory by entity type
  3. 03Query or remove relationships by type

MCP support

It exposes graph memory tools to MCP clients for creating, querying, and deleting entities and relationships.

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

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Graph Memory RAG MCP Server

A Model Context Protocol (MCP) server implementation that provides graph-based memory storage capabilities. This server allows AI agents to store and retrieve information in a graph structure, making it ideal for maintaining context and relationships between different pieces of information.

Features

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

Installation

npm install

Dependencies

  • @modelcontextprotocol/sdk: ^1.0.3
  • zod: ^3.22.4

Usage

Start the server:

node app.js

API Tools

Create Entity

Creates a new entity in the graph database.

  • Parameters:
    • name: string
    • entityType: string
    • observations: string[]
Create Relationship

Creates a relationship between two existing entities.

  • Parameters:
    • fromEntityName: string
    • toEntityName: string
    • relationType: string
Query Entities

Retrieves entities by type.

  • Parameters:
    • entityType: string
Query Relationships

Retrieves relationships by type.

  • Parameters:
    • relationType: string
Delete Entity

Deletes an entity and its associated relationships.

  • Parameters:
    • name: string

Implementation Details

The server uses an in-memory graph database with two main components:

  1. Entities Map: Stores entity objects with their properties
  2. Relationships Map: Stores relationship objects connecting entities

Each entity contains:

  • id: Unique identifier
  • name: Entity name
  • type: Entity type
  • observations: Array of strings containing information about the entity

Each relationship contains:

  • id: Unique identifier
  • fromId: Source entity ID
  • toId: Target entity ID
  • type: Relationship type

Contributing

Feel free to open issues or submit pull requests for improvements.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.