Lithtrix — Identity, Memory & Trust for AI Agents

Overview

Lithtrix — Identity, Memory & Trust for AI Agents is a Model Context Protocol (MCP) server: Identity, memory, trust, and swarm primitives for AI agents. MIRC base always free. In practice that means any MCP-compatible AI assistant can call Lithtrix — Identity, Memory & Trust for AI Agents's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the npm package lithtrix-mcp speaks MCP over stdio on your machine. Configuration happens through environment variables — you'll need LITHTRIX_API_KEY. The current release is v0.20.2, with source at lithtrix/lithtrix-mcp on GitHub.

Lithtrix — Identity, Memory & Trust for AI Agents is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Lithtrix — Identity, Memory & Trust for AI Agents for lithtrix.ai, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "lithtrix_identity_memory_trust_for_ai_agents": {
      "command": "npx",
      "args": [
        "-y",
        "lithtrix-mcp"
      ],
      "env": {
        "LITHTRIX_API_KEY": "<lithtrix-api-key>"
      }
    }
  }
}

Requires LITHTRIX_API_KEY