Memory Graph Server
A Model Context Protocol server that provides knowledge graph management capabilities.
What is Memory Graph Server?
Memory Graph Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol server that provides knowledge graph management capabilities.
A Model Context Protocol server that provides knowledge graph management capabilities.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol server that provides knowledge grap
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx memory-mcp-server-goConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Memory Graph Server
Memory MCP Server Go (mms) is a high-performance knowledge graph server written in Go that gives AI assistants persistent, structured memory across conversations. It stores entities, observations, and relations in a local SQLite file and exposes tools for creating, querying, merging, and updating graph nodes using full-text search with synonym expansion. Unlike ephemeral conversation context, the knowledge graph persists between sessions, allowing the AI to recall facts about projects, people, or concepts it has learned over time. The server supports stdio, SSE, and HTTP transports and can be secured with OAuth 2.1 or bearer token authentication.
Prerequisites
- macOS, Linux, or Windows (pre-built binaries available for all three)
- Go 1.24+ (only if building from source; not needed for Homebrew or binary installs)
- Write access to a directory for the memory.json storage file
- An MCP client such as Claude Desktop, VS Code, or Cursor
Install the mms binary
Install via Homebrew on macOS (easiest) or use the curl installer on any Unix system. Alternatively download a pre-built binary from the GitHub Releases page.
# Homebrew (macOS)
brew install okooo5km/tap/mms
# Curl installer (macOS/Linux)
curl -fsSL https://raw.githubusercontent.com/okooo5km/memory-mcp-server-go/main/scripts/install.sh | bash
# Verify installation
mms --versionChoose a memory storage location
Decide where the knowledge graph file (memory.json) will live. A dedicated directory in your home folder works well. The directory must exist before the server starts.
mkdir -p ~/.config/mmsConfigure your MCP client
Add the memory server to your MCP client config. Set MEMORY_FILE_PATH to the full path where you want the knowledge graph stored.
{
"mcpServers": {
"memory": {
"command": "mms",
"env": {
"MEMORY_FILE_PATH": "/Users/you/.config/mms/memory.json"
}
}
}
}Restart your MCP client
Restart your MCP client so it starts the mms server. On first run, mms will create the memory.json file automatically if it does not exist.
Verify with a test entity
Ask your AI assistant to create a test entity in the knowledge graph, then retrieve it to confirm read/write access is working.
Memory Graph Server Examples
Client configuration
Claude Desktop config for the Memory MCP Server Go binary with a custom memory file path.
{
"mcpServers": {
"memory": {
"command": "mms",
"env": {
"MEMORY_FILE_PATH": "/Users/you/.config/mms/memory.json"
}
}
}
}Prompts to try
Examples of how to use the persistent knowledge graph through your AI assistant.
- "Remember that my project 'Atlas' uses PostgreSQL 15 and is deployed on AWS us-east-1."
- "Create an entity for Alice Chen, noting she is the lead engineer on project Atlas."
- "What do you know about project Atlas?"
- "Search your memory for everything related to PostgreSQL."
- "Update your memory: project Atlas has been migrated to AWS us-west-2."Troubleshooting Memory Graph Server
mms fails to start with 'cannot open memory file' error
Ensure the directory containing the MEMORY_FILE_PATH exists. mms creates the file itself but not the parent directory. Run 'mkdir -p /path/to/directory' then restart the MCP client.
search_nodes returns no results even for recently created entities
The FTS5 full-text search index may need a moment to update after new entities are created. Try open_nodes or read_graph to browse all entities directly. If results are consistently missing, check that the MEMORY_FILE_PATH is the same path used when creating entities.
'mms: command not found' in the MCP client
The Homebrew or curl install may have placed the binary in a directory not on the PATH seen by the MCP client (which may not load shell profiles). Use the full absolute path to the mms binary in your config: run 'which mms' to find it, then set 'command' to that full path.
Frequently Asked Questions about Memory Graph Server
What is Memory Graph Server?
Memory Graph Server is a Model Context Protocol (MCP) server that model context protocol server that provides knowledge graph management capabilities. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Memory Graph Server?
Follow the installation instructions on the Memory Graph Server GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Memory Graph Server?
Memory Graph Server works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Memory Graph Server free to use?
Yes, Memory Graph Server is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Memory Graph Server Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Memory Graph Server? 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 Memory Graph Server 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 Memory Graph Server?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.