MCP server by Auctalis · ★ 3 · updated 2 months ago
Agent reasoning, memory, and token-optimized context for AI applications.
Choose your AI client and copy the config.
Add to claude_desktop_config.json — macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Then restart Claude. Setup guide
{
"mcpServers": {
"nocturnusai": {
"command": "npx",
"args": [
"-y",
"nocturnusai-mcp"
]
}
}
}Or add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project). Setup guide
{
"mcpServers": {
"nocturnusai": {
"command": "npx",
"args": [
"-y",
"nocturnusai-mcp"
]
}
}
}Or add to .vscode/mcp.json in your workspace. Setup guide
{
"servers": {
"nocturnusai": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"nocturnusai-mcp"
]
}
}
}Cascade → Actions → Open MCP config file (often ~/.config/devin/mcp_config.json). Setup guide
{
"mcpServers": {
"nocturnusai": {
"command": "npx",
"args": [
"-y",
"nocturnusai-mcp"
]
}
}
}Run in your terminal: Setup guide
claude mcp add nocturnusai -- npx -y nocturnusai-mcpCLI or add to ~/.codex/config.toml. Setup guide
codex mcp add nocturnusai -- npx -y nocturnusai-mcp[mcp_servers.nocturnusai]
command = "npx"
args = ["-y", "nocturnusai-mcp"]Cline panel → Configure MCP Servers, or ~/.cline/data/settings/cline_mcp_settings.json. Setup guide
{
"mcpServers": {
"nocturnusai": {
"command": "npx",
"args": [
"-y",
"nocturnusai-mcp"
]
}
}
}Run the server directly:
npx -y nocturnusai-mcpBasic persistent memory using a local knowledge graph of entities, relations and observations, so the assistant can remember information about you across chats.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.
A Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.