NFTIAI
NFTI AI — NFTI your AI Agents & Virtual IP. Bridging intelligent agents, MCP protocols, and RWA to create a new era of digital sovereignty.
claude mcp add --transport stdio axarb-nftiai npx -y @nfti/core
How to use
NFTIAI is a MCP-compatible framework/library that enables you to run NFTI’s AI agent ecosystem within an MCP-enabled environment. It provides a standard way to instantiate digital identity tools, RWA registries, and agent-enabled capabilities that can be invoked by LLMs through MCP adapters. Once started, you can leverage NFTI’s IdentityClient, RWARegistryClient, and related tools to perform tasks such as querying profiles, coordinating with RWA registries, and exposing agent-based capabilities as MCP tools for orchestration across contexts and boundaries. The included tooling supports interaction with major AI SDKs, making it straightforward to integrate NFTI’s agents and tools into your existing LLM workflows and MCP gateways.
How to install
Prerequisites:
- Node.js and npm installed on your system (recommended LTS release)
- Internet access to fetch the NFTI core package
Installation steps:
- Check Node.js and npm versions node -v npm -v
- Create a project directory (if needed) and initialize a package.json mkdir nfti-mcp-server && cd nfti-mcp-server npm init -y
- Install NFTI core as a dependency (or use npx directly later) npm install @nfti/core
- Verify installation by listing node_modules ls node_modules/@nfti/core
- Alternative run using npx without local install npx -y @nfti/core
Usage:
- After installation, you can initialize NFTI clients (IdentityClient, RWARegistryClient) in your MCP-enabled workflow and expose them as MCP tools or gateways as appropriate for your setup.
Additional notes
Tips and common issues:
- Ensure your environment has network access to fetch npm packages and any external MCP gateway endpoints.
- NFTI relies on MCP adapters to bridge tools into LLM toolchains; ensure MCP gateway clients are configured if you plan to connect to other MCP contexts.
- If you encounter permission issues with npx, try running with sudo on Unix-like systems or ensure npm permissions are properly configured.
- Review NFTI’s documentation for specific tool names (IdentityClient, RWARegistryClient) and their methods to expose as MCP tools.
- Environment variables may be used to configure API endpoints, credentials, or registry URLs; refer to NFTI documentation for the exact vars required by your deployment (e.g., NFTI_RWA_REGISTRY_URL, NFTI_MCP_GATEWAY).
Related MCP Servers
Remote
A type-safe solution to remote MCP communication, enabling effortless integration for centralized management of Model Context.
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
CanvasMCPClient
Canvas MCP Client is an open-source, self-hostable dashboard application built around an infinite, zoomable, and pannable canvas. It provides a unified interface for interacting with multiple MCP (Model Context Protocol) servers through a flexible, widget-based system.
marinade-finance
Marinade Finance MCP Server is an MCP server specifically designed for the Marinade Finance.
google-scholar
An MCP server for Google Scholar written in TypeScript with Streamable HTTP
mcp -blog
Example of a MCP implementation using TypeScript and OAuth.