AI Plugin Index
Server Memory
Verified · npm:@modelcontextprotocolMCP server by modelcontextprotocol · updated · ★ 91k · 139k downloads a week
MCP server for enabling memory for Claude through a knowledge graph Server Memory is published by npm:@modelcontextprotocol from its verified domain in the official MCP Registry.
Last commit 2 days ago
No licence found, so reuse rights are unclear
Clear description, published package or server URL, 91,404 stars, original repository
Not checked yet. What we check
Install Server Memory
Built from the published package, never by AIclaude mcp add server-memory -- npx -y @modelcontextprotocol/server-memoryRun in your terminal. Add --scope user to use it in every project.
{
"mcpServers": {
"server-memory": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
}
}
}Settings, Developer, Edit config. Paste into claude_desktop_config.json and restart.
{
"mcpServers": {
"server-memory": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
}
}
}Add to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project).
{
"servers": {
"server-memory": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
}
}
}Add to .vscode/mcp.json. VS Code uses "servers", not "mcpServers".
codex mcp add server-memory -- npx -y @modelcontextprotocol/server-memory{
"mcpServers": {
"server-memory": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
}
}
}Add to ~/.gemini/config/mcp_config.json (all projects) or .agents/mcp_config.json (this project).
gemini mcp add server-memory npx -y @modelcontextprotocol/server-memoryGemini CLI was replaced by Antigravity CLI in June 2026 and remains only for enterprise licences and paid API keys.
MCP servers run with your permissions and can read what you give them access to. Some need an API key: check the README and add it under env in the server-memory block.
Alternatives to Server Memory
All alternatives →
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Standalone Model Context Protocol client for pi and other applications
MCP (Model Context Protocol) adapter extension for Pi coding agent
MCP (Model Context Protocol) client extension for the Pi coding agent — connect Pi to any MCP server
Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code
Server Memory: common questions
How do I install Server Memory?
In Claude Code run claude mcp add server-memory -- npx -y @modelcontextprotocol/server-memory. For Claude Desktop, Cursor and VS Code, paste the config shown above and restart. See the install guides.
Is Server Memory the official server?
Server Memory is published by npm:@modelcontextprotocol from its verified domain in the official MCP Registry.
Is Server Memory free?
The code is published under the NOASSERTION licence. The service it connects to may have its own pricing.
Is Server Memory safe to use?
It scores 88 of 100. Grades: maintenance A, licence F, quality A. The security check has not run for it yet. Review the code before you install. How grades work.
What are alternatives to Server Memory?
Similar MCP servers: Codebase Memory, ha-mcp, Pi MCP, Pi MCP Adapter.
Does Server Memory work with ChatGPT?
Not directly. It runs locally, and ChatGPT only connects to remote servers with a URL. Use it in Claude Code, Claude Desktop, Cursor, VS Code or Codex.