Alaya MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 126 installs a week from npm. Last commit 16 Jul 2026.
Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall
We read the source, 3 d ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
alaya-mcp похож на laya-mcp
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
postinstall: node scripts/postinstall.js
const result = require("child_process").spawnSync(binary, process.argv.slice(2), {
return path.join(pkgDir, binary);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Alaya MCP and you get told the day something new turns up.
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 alaya-mcp -- npx -y alaya-mcp
{
"mcpServers": {
"alaya-mcp": {
"command": "npx",
"args": [
"-y",
"alaya-mcp"
]
}
}
}
[mcp_servers.alaya-mcp]
command = "npx"
args = ["-y", "alaya-mcp"]
{
"mcpServers": {
"alaya-mcp": {
"command": "npx",
"args": [
"-y",
"alaya-mcp"
]
}
}
}
{
"servers": {
"alaya-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"alaya-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
ALAYA_LLM_API_KEY (API key for auto-consolidation (enables LLM-powered knowledge extraction)), ALAYA_LLM_API_URL (OpenAI-compatible chat completions endpoint), ALAYA_LLM_MODEL (Model name (e.g. gpt-4o-mini, haiku, gemini-flash)), ALAYA_DB (Path to SQLite database).
Long-term memory and a knowledge graph for AI agents: recall, notes, secrets and data sources.
Zero-Trust PII & secrets sanitizer for AI agents with in-memory local redaction.
Secure durable memory and bounded context for AI agents, with hosted OAuth and local Lite support.
Real-time semantic security for AI coding agents and MCP tools
Agentic SDLC governance and security controls for AI coding agents working with GitHub.
Secure encoding-aware local workspace runtime for AI agents
Agent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.
MCP server for AI assistants: read, write, edit, and manage files securely on local filesystem.
Answers built from our own checks of this server.