MCP Memory with Redis Graph

@samwang0723

About MCP Memory with Redis Graph

MCP Server for long term memory graph

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-memory": {
      "command": "docker",
      "args": [
        "exec",
        "-it",
        "mcp-memory-redis-1",
        "redis-cli"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Memory with Redis Graph?

MCP Memory with Redis Graph is a server that implements a memory system for LLM conversations, using Redis Graph as a backend to store memories as nodes in a knowledge graph. It’s designed for developers and AI assistants who need persistent, relational memory for context across sessions.

How to use MCP Memory with Redis Graph?

Run Redis with the RedisGraph module via Docker Compose, then install dependencies with npm install and start the application with npm start. The server exposes tools for creating, retrieving, searching, updating, and deleting memories, as well as managing relationships between them.

Key features of MCP Memory with Redis Graph

Supports eight memory types: Conversation, Topic, Project, Task, Issue, Config, Finance, Todo
Creates and retrieves relationships between memories via create_relation and get_related_memories
Searches memories by type, keyword, and other criteria
Updates and deletes existing memories
Uses Redis Graph for graph-based storage and queries
Provides helper scripts for Redis CLI, graph inspection, and testing

Use cases of MCP Memory with Redis Graph

Store project details and configurations for long-term reference
Record and track issues or bugs with severity and status
Save financial advice and investment recommendations
Manage work-related todo items with priorities and completion status

FAQ from MCP Memory with Redis Graph

What runtime dependencies are required?

Docker and Docker Compose, Node.js v16 or higher, and a Redis instance with the RedisGraph module.

How do I configure the Redis connection?

By default, the application connects to localhost:6379. Update the Redis client configuration in src/index.ts to change host or port.

Can I run the server in Docker?

Yes, build the Docker image with docker build -t mcp/memory . and run it on the same network as Redis, passing the REDIS_URL environment variable.

What transport does the server use?

The README does not specify transport details; it uses the MCP protocol for tool invocation.

How do I inspect the graph data?

Use npm run check:graph to see all nodes, Finance memories, and relationships, or npm run inspect:graph for a detailed schema and contents.

Frequently asked questions

What runtime dependencies are required?

Docker and Docker Compose, Node.js v16 or higher, and a Redis instance with the RedisGraph module.

How do I configure the Redis connection?

By default, the application connects to localhost:6379. Update the Redis client configuration in `src/index.ts` to change host or port.

Can I run the server in Docker?

Yes, build the Docker image with `docker build -t mcp/memory .` and run it on the same network as Redis, passing the `REDIS_URL` environment variable.

What transport does the server use?

The README does not specify transport details; it uses the MCP protocol for tool invocation.

How do I inspect the graph data?

Use `npm run check:graph` to see all nodes, Finance memories, and relationships, or `npm run inspect:graph` for a detailed schema and contents.

Comments

Basic information

More Memory & Knowledge MCP servers

Memory

modelcontextprotocol

Model Context Protocol Servers

88.1K

Mcp Knowledge Graph

shaneholloman

MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development

871

Context Portal MCP (ConPort)

GreatScottyMac

Context Portal (ConPort): A memory bank MCP server building a project-specific knowledge graph to supercharge AI assistants. Enables powerful Retrieval Augmented Generation (RAG) for context-aware development in your IDE.

763

📓 GistPad MCP

lostintangent

📓 An MCP server for managing your personal knowledge, daily notes, and re-usable prompts via GitHub Gists

199

Solomd

zhitongblog

A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.

425