Knowledge Graph Memory Server MCP Server

@s2005

Repository

Basic information

About Knowledge Graph Memory Server MCP Server

Standalone MCP server for enabling memory for Claude through a knowledge graph

#knowledge-graph #memory-server #ai-assistant

Knowledge Graph Memory Server MCP Server config

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

{
  "mcpServers": {
    "mcp-memory-server": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "mcp/memory",
        "-f",
        "src/Dockerfile",
        "."
      ]
    }
  }
}

Knowledge Graph Memory Server MCP Server tools

Create multiple new entities in the knowledge graph

Create multiple new relations between entities

Add new observations to existing entities

Remove entities and their relations

Remove specific observations from entities

Remove specific relations from the graph

Read the entire knowledge graph

Search for nodes based on query

Retrieve specific nodes by name

Overview

What is Knowledge Graph Memory Server?

A basic implementation of persistent memory using a local knowledge graph. It lets Claude remember information about the user across chats by storing entities, relations, and observations.

How to use Knowledge Graph Memory Server?

Add the server configuration to claude_desktop_config.json using Docker (recommended) or NPX. Optionally set the MEMORY_FILE_PATH environment variable to customize the storage location. Use the provided system prompt example in a Claude.ai Project to enable memory operations.

Key features of Knowledge Graph Memory Server

Persistent, local knowledge graph for chat context
Tools to create, read, update, and delete entities, relations, and observations
Full search functionality across names, types, and observations
Silent handling of duplicate entities and relations
Cascading deletion of relations when entities are removed
Customizable memory file path via environment variable

Use cases of Knowledge Graph Memory Server

Chat personalization: remember user identity, preferences, and behaviors across sessions
Tracking personal and professional relationships with up to 3 degrees of separation
Storing recurring organizations, people, and significant events as structured entities
Maintaining a persistent knowledge base for long-running interactions

Frequently asked questions

Where is the memory data stored?

By default in `memory.json` in the server directory. You can change this by setting the `MEMORY_FILE_PATH` environment variable.

How do I run it with Docker?

Add the Docker configuration from the README to `claude_desktop_config.json`. The Docker command mounts a volume `claude-memory` for persistence and runs the `mcp/memory` image.

Can I use it as a standalone package?

Yes. Install the npm package `mcp-memory-server` or run directly with `npx mcp-memory-server`.

What happens if I create an entity with an existing name?

The server ignores duplicate entity names when using `create_entities`. Similarly, duplicate relations are skipped.

What license does Knowledge Graph Memory Server use?

It is licensed under the MIT License.

Comments

More Memory & Knowledge MCP servers

Azquo

Azquo Holdings Ltd

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,

Neither MCP

stonianua

Project context your AI can query through MCP — with source evidence.

UmmahAPI

Yousuf Kazmi

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths

M1K3

Round-Tower

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.

server-noonien - shared memory MCP

sequico

Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.