Knowledge Graph Memory Server
@s2005
About Knowledge Graph Memory Server
Standalone MCP server for enabling memory for Claude through a knowledge graph
Basic information
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",
"."
]
}
}
}Tools
9Create 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
FAQ from Knowledge Graph Memory Server
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.
More Memory & Knowledge MCP servers
Solomd
zhitongblogA 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.
MCP server for Obsidian
MarkusPfundsteinMCP server that interacts with Obsidian via the Obsidian rest API community plugin
Notion MCP Server
makenotionOfficial Notion MCP Server
Memory
modelcontextprotocolModel Context Protocol Servers
Context Portal MCP (ConPort)
GreatScottyMacContext 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.
Comments