MCP Knowledge Graph
An improved implementation of persistent memory using a local knowledge graph with a customizable --memory-path. This lets Claude remember information about the user across chats.
What is MCP Knowledge Graph?
MCP Knowledge Graph is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to improved implementation of persistent memory using a local knowledge graph with a customizable --memory-path. this lets claude remember information about the user across chats.
An improved implementation of persistent memory using a local knowledge graph with a customizable --memory-path. This lets Claude remember information about the user across chats.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- create_entities
- create_relations
- add_observations
- delete_entities
- delete_observations
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @itseasy21/mcp-knowledge-graphManual Installation
npx -y @itseasy21/mcp-knowledge-graphConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Knowledge Graph
MCP Knowledge Graph (@itseasy21/mcp-knowledge-graph) is an improved implementation of persistent memory for Claude that uses a local knowledge graph stored as a file on your machine. It lets Claude remember entities (people, projects, concepts), facts about them, and the relationships between them across separate chat sessions, with all data stored locally so nothing is sent to third-party cloud services. The --memory-path flag lets you place the graph in any directory, including cloud-synced folders, so your memory is portable across devices.
Prerequisites
- Node.js 22 or later installed
- npx available on your PATH
- Claude Desktop or another MCP-compatible client
- A writable directory for memory storage (e.g. ~/.aim or a cloud-synced folder)
Choose a memory storage directory
Pick a directory where the knowledge graph file will be stored. Using a cloud-synced folder (e.g. ~/Library/Mobile Documents or a Dropbox path) makes your memory available on all your devices.
mkdir -p ~/.aimAdd the server to Claude Desktop configuration
Edit claude_desktop_config.json and add the mcp-knowledge-graph entry, passing your chosen directory via --memory-path.
{
"mcpServers": {
"knowledge-graph": {
"command": "npx",
"args": [
"-y",
"@itseasy21/mcp-knowledge-graph",
"--memory-path",
"/Users/yourname/.aim"
]
}
}
}Restart Claude Desktop
Quit and reopen Claude Desktop. The knowledge-graph server will start automatically and the 11 memory tools will become available.
Ask Claude to store a memory
Test the connection by asking Claude to remember something. It will use the aim_memory_store tool to create an entity in the local graph.
Verify persistence across sessions
Close the Claude Desktop chat, start a new conversation, and ask Claude to recall the information you stored. It will use aim_memory_search or aim_memory_get to retrieve it from disk.
MCP Knowledge Graph Examples
Client configuration
Claude Desktop config with memory stored in ~/.aim. Adjust the path to match your chosen directory.
{
"mcpServers": {
"knowledge-graph": {
"command": "npx",
"args": [
"-y",
"@itseasy21/mcp-knowledge-graph",
"--memory-path",
"/Users/yourname/.aim"
]
}
}
}Prompts to try
Use these prompts to exercise memory storage and retrieval across sessions.
- "Remember that my colleague Alice works on the payments team and prefers Python."
- "What do you know about Alice?"
- "Link my 'Project Alpha' memory to Alice since she is the lead engineer."
- "Forget everything you know about Project Beta — it was cancelled."
- "Search your memory for anything related to the authentication service."Troubleshooting MCP Knowledge Graph
Claude says it cannot remember things or the tools are not available
Confirm the memory-path directory exists and is writable. Verify Node.js 22+ is installed with 'node --version'. Restart Claude Desktop and check the MCP servers panel for errors next to the knowledge-graph entry.
Memory is not persisting across chat sessions
Make sure you are always using the same --memory-path value in the config. If the path contains spaces or special characters, wrap it in quotes in the JSON config array.
npx fails to download @itseasy21/mcp-knowledge-graph
Check your internet connection and npm registry access. Try 'npm install -g @itseasy21/mcp-knowledge-graph' to install globally and then change the command in the config to the global binary path.
Frequently Asked Questions about MCP Knowledge Graph
What is MCP Knowledge Graph?
MCP Knowledge Graph is a Model Context Protocol (MCP) server that improved implementation of persistent memory using a local knowledge graph with a customizable --memory-path. this lets claude remember information about the user across chats. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Knowledge Graph?
Install via npm with the command: npx -y @itseasy21/mcp-knowledge-graph. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with MCP Knowledge Graph?
MCP Knowledge Graph works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Knowledge Graph free to use?
Yes, MCP Knowledge Graph is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
MCP Knowledge Graph Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to MCP Knowledge Graph? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Knowledge Graph in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Knowledge Graph?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.