NSAF MCP Server

Source

The Neuro-Symbolic Autonomy Framework integrates neural, symbolic, and autonomous learning methods into a single, continuously evolving AI agent-building system. This prototype demonstrates the SCMA component, which enables AI agents to self-design new AI agents using Generative Architecture Models.

Catalog onlyCatalog onlySTDIO

Overview

The NSAF MCP Server is a Model Context Protocol server for the Neuro-Symbolic Autonomy Framework (NSAF), which integrates neural, symbolic, and autonomous learning methods into a single AI agent-building system. This prototype showcases the SCMA component, allowing AI agents to self-design new agents using Generative Architecture Models.

To use the NSAF MCP Server, clone the repository from GitHub, install the necessary dependencies, and run the server locally. You can also deploy it to GitHub and configure it for use with AI assistants like Claude.

Run NSAF evolution with customizable parameters. - Compare different NSAF agent architectures. - Integrate NSAF capabilities into AI assistants.

Developing AI agents that can evolve and adapt over time.
Comparing various architectures for AI agents to determine the most effective designs.
Enhancing AI assistants with advanced capabilities through the NSAF framework.

Add to your AI client

Use these steps to connect NSAF MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "nsaf-mcp-server-ariunbolor": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-nsaf-mcp-server-ariunbolor"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "nsaf-mcp-server-ariunbolor": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-nsaf-mcp-server-ariunbolor"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "nsaf-mcp-server-ariunbolor": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-nsaf-mcp-server-ariunbolor"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "nsaf-mcp-server-ariunbolor": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-nsaf-mcp-server-ariunbolor"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "nsaf-mcp-server-ariunbolor": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-nsaf-mcp-server-ariunbolor"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "nsaf-mcp-server-ariunbolor": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-nsaf-mcp-server-ariunbolor"
      ]
    }
  }
}

FAQ

What are the prerequisites for using NSAF MCP Server?

You need Node.js 18+ and npm, as well as Python 3.8+ with the NSAF framework installed.

Can I deploy NSAF MCP Server on GitHub?

Yes! You can create a new GitHub repository and use the provided setup script to push your code.

How do I configure the server for AI assistants?

You need to add the server to your MCP settings configuration in the respective AI assistant application.

Research and data