Nex runs on your own machine — the client starts it, so there is no endpoint to ping. 133 installs a week from npm.
Organizational context & memory for AI agents. Connect 100+ tools into one knowledge graph.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add nex -- npx -y @nex-ai/nex
{
"mcpServers": {
"nex": {
"args": [
"-y",
"@nex-ai/nex"
],
"command": "npx"
}
}
}
[mcp_servers.nex]
command = "npx"
args = ["-y", "@nex-ai/nex"]
{
"mcpServers": {
"nex": {
"args": [
"-y",
"@nex-ai/nex"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"nex": {
"args": [
"-y",
"@nex-ai/nex"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
NEX_API_KEY (Your Nex API key. Sign up at https://nex.ai or use the 'register' tool to get one.).
The author declared them in the registry entry; get the values from the project itself.
Cognitive memory for AI agents. Atkinson-Shiffrin, RAG, knowledge graph. 100+ tools.
Code knowledge graph over MCP: token-budgeted context for AI coding agents.
Knowledge-graph memory server for AI tools via MCP
Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP.
MCP adapter for Engram - organizational memory for AI agents
Universal memory for AI agents and tools. Save, organize and search context anywhere.
Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation
Operational memory for AI agents: code graph, session memory & guardrails. No context rot.
Answers built from our own checks of this server.