MCPLow riskUnclaimed

alaya-mcp

Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall

SecurityRoninsecurityronin/alaya-mcp★ 17Updated Mar 27, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.SecurityRonin/alaya-mcp",
  "description": "Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall",
  "repository": {
    "url": "https://github.com/SecurityRonin/alaya",
    "source": "github",
    "subfolder": "npm/alaya-mcp"
  },
  "version": "0.4.7",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "alaya-mcp",
      "version": "0.4.7",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "API key for auto-consolidation (enables LLM-powered knowledge extraction)",
          "format": "string",
          "isSecret": true,
          "name": "ALAYA_LLM_API_KEY"
        },
        {
          "description": "OpenAI-compatible chat completions endpoint",
          "format": "string",
          "name": "ALAYA_LLM_API_URL"
        },
        {
          "description": "Model name (e.g. gpt-4o-mini, haiku, gemini-flash)",
          "format": "string",
          "name": "ALAYA_LLM_MODEL"
        },
        {
          "description": "Path to SQLite database",
          "format": "string",
          "name": "ALAYA_DB"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:alaya-mcp@0.4.7
Runs install scripts—npm:alaya-mcp
NetworkNoneNone
Needs credentialsALAYA_LLM_API_KEYALAYA_LLM_API_KEY
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.4.7latestOct 7, 2026