AI Tools: Installation

Each AI surface installs independently. Pick the one that matches what you are building, or install the MCP gateway first since it is the smallest step to a working tool call.

Surface	Install path	Prerequisites
MCP servers	`npx` for the gateway, local build for the focused servers	Node.js 18+, an MCP host
KaleidoAgent	Clone and build from source	Node.js 20+, KaleidoCLI, Nanobot, an LLM API key
KaleidoMind	Ships inside the Desktop App, or build the repo for development	Desktop App, or pnpm and the QVAC SDK

Every surface here signs with a real BIP-39 mnemonic or drives a live node. Start on test networks, keep dry_run enabled until a setup is verified, and never put a mainnet seed in a file you commit or share.

MCP Servers

kaleido-mcp is the fastest path to a working tool call, published to npm with no local build required:

npx -y kaleido-mcp

Two per-wallet servers, wdk-wallet-mcp and wdk-wallet-spark-mcp, remain standalone rather than folded into the gateway and build from source:

git clone https://github.com/kaleidoswap/wdk-wallet-mcp.git
cd wdk-wallet-mcp
npm install
npm run build
node dist/index.js

kaleidoswap-mcp and l402-gateway-mcp are archived, their own READMEs point integrators at kaleido-mcp instead. Do not clone or build them for a new setup.

Full environment variable reference, stdio vs. HTTP transport, the tool surface, and client config JSON for every server live on the MCP Servers page.

KaleidoAgent

Prerequisites: Node.js 20 or newer, KaleidoCLI in $PATH, the Nanobot runtime, and an Anthropic or OpenAI API key.

git clone https://github.com/kaleidoswap/kaleido-agent.git
cd kaleido-agent
npm run install:all

From there, setting the API key, configuring the wallet in agent.config.json, and starting the dashboard are covered step by step on the KaleidoAgent page, along with the container deployment option.

KaleidoMind

KaleidoMind is an engine embedded in a host application rather than a standalone install.

Through the Desktop App

The fastest path. The Desktop App bundles the engine as in-app chat, manages the on-device model lifecycle, and can act as the paired inference peer a phone delegates to. Switch it on from Settings > Capabilities by selecting Node + Mind or Only Mind.

KaleidoMind depends on a local AI runtime and may not be available on Windows yet. Every trading and node feature works without it, so run the app in Only Node mode if Mind is unavailable on your platform.

From source, for development

git clone https://github.com/kaleidoswap/kaleido-mind.git
cd kaleido-mind
pnpm install && pnpm -r build

The CLI in apps/cli handles on-device model management and runs the agent directly:

cd apps/cli
npx tsx src/index.ts setup     # guided first run: pick and pull a model
npx tsx src/index.ts run "what's my balance?"
npx tsx src/index.ts skills    # list installed skills

To exercise the engine against a model without a phone, use the playground from the repository root:

pnpm play "pay bob 3 eur"

Introduction

Tools

Reference

MCP Servers

KaleidoAgent

KaleidoMind

Through the Desktop App

From source, for development

​MCP Servers

​KaleidoAgent

​KaleidoMind

​Through the Desktop App

​From source, for development

MCP Servers

KaleidoAgent

KaleidoMind

Through the Desktop App

From source, for development