Skip to main content
Glama

NSAF MCP Server

NSAF MCP Server

This is a Model Context Protocol (MCP) server for the Neuro-Symbolic Autonomy Framework (NSAF). It allows AI assistants to interact with the NSAF framework through the MCP protocol.

Note: This repository includes both the NSAF framework code and the MCP server implementation, making it a complete package that can be deployed and used anywhere.

Note: This implementation uses a simplified version of the MCP protocol that doesn't require the official MCP SDK. It implements the core functionality needed to expose NSAF capabilities to AI assistants.

Features

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

Prerequisites

  • Node.js 18+ and npm
  • Python 3.8+ with the NSAF framework installed

Installation

  1. Clone this repository:
git clone https://github.com/ariunbolor/nsaf-mcp-server.git cd nsaf-mcp-server
  1. Install dependencies:
npm install
  1. Build the server:
npm run build

Configuration

The server includes the NSAF framework code, so no additional configuration is required for basic usage. The MCP server is designed to work out-of-the-box when installed globally.

Usage

Running the server locally

npm start

Deploying to GitHub

  1. Create a new GitHub repository for your MCP server:
    • Go to GitHub and create a new repository named nsaf-mcp-server
    • Initialize it with a README file
  2. Use the provided setup script to push your code to GitHub:
# For a new repository ./setup-github-fixed.sh yourusername # If the repository already exists and you want to overwrite its content ./setup-github-fixed.sh yourusername --force

The script will:

  • Initialize git if needed
  • Set up the remote repository
  • Commit your changes
  • Try to push to GitHub (with options to handle existing repositories)
  1. Configure GitHub Actions for CI/CD (optional):
    • Create a .github/workflows directory
    • Add a workflow file for testing and building the server

Using with AI Assistants

To use this MCP server with AI assistants like Claude, you need to:

  1. Install the server:Option 1: Install from GitHub (after pushing your code):
    npm install -g yourusername/nsaf-mcp-server
    Option 2: Install from your local directory:
    # Navigate to the nsaf-mcp-server directory cd nsaf_mcp_server # Install dependencies and build npm install npm run build # Install globally from the local directory npm install -g .
  2. Add the server to your MCP settings configuration:

For Claude Desktop app, edit ~/Library/Application Support/Claude/claude_desktop_config.json (on macOS):

{ "mcpServers": { "nsaf": { "command": "nsaf-mcp-server", "args": [], "env": {}, "disabled": false, "autoApprove": [] } } }

For Cline, edit /Users/onthego/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json:

{ "mcpServers": { "nsaf": { "command": "nsaf-mcp-server", "args": [], "env": {}, "disabled": false, "autoApprove": [] } } }

Available Tools

run_nsaf_evolution

Run NSAF evolution with specified parameters.

Parameters:

  • population_size: Size of the agent population (default: 20)
  • generations: Number of generations to evolve (default: 10)
  • mutation_rate: Mutation rate (0.0-1.0) (default: 0.2)
  • crossover_rate: Crossover rate (0.0-1.0) (default: 0.7)
  • architecture_complexity: Complexity of the agent architecture ('simple', 'medium', 'complex') (default: 'medium')

compare_nsaf_agents

Compare different NSAF agent architectures.

Parameters:

  • architectures: List of architectures to compare (default: ['simple', 'medium', 'complex'])

License

MIT

-
security - not tested
A
license - permissive license
-
quality - not tested

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

AI アシスタントが Neuro-Symbolic Autonomy Framework と対話できるようにし、カスタマイズ可能なパラメータを使用して NSAF の進化を実行したり、さまざまなエージェント アーキテクチャを比較したりする機能を有効にするモデル コンテキスト プロトコル サーバー。

  1. 特徴
    1. 前提条件
      1. インストール
        1. 構成
          1. 使用法
            1. ローカルでサーバーを実行する
            2. GitHubへのデプロイ
            3. AIアシスタントと併用する
          2. 利用可能なツール
            1. ラン_nsaf_evolution
            2. nsafエージェントの比較
          3. ライセンス

            Related MCP Servers

            • -
              security
              F
              license
              -
              quality
              A comprehensive Model Context Protocol server implementation that enables AI assistants to interact with file systems, databases, GitHub repositories, web resources, and system tools while maintaining security and control.
              Last updated -
              6
              1
            • -
              security
              A
              license
              -
              quality
              A Model Context Protocol server that enhances AI agents by providing deep semantic understanding of codebases, enabling more intelligent interactions through advanced code search and contextual awareness.
              Last updated -
              49
              MIT License
              • Apple
            • -
              security
              F
              license
              -
              quality
              A Model Context Protocol server that provides AI models with structured access to external data and services, acting as a bridge between AI assistants and applications, databases, and APIs in a standardized, secure way.
              Last updated -
              2
            • A
              security
              A
              license
              A
              quality
              A Model Context Protocol server that enables AI assistants to communicate with each other using Inter-Process Communication, featuring natural language commands and cross-platform compatibility.
              Last updated -
              9
              89
              MIT License

            View all related MCP servers

            MCP directory API

            We provide all the information about MCP servers via our MCP API.

            curl -X GET 'https://glama.ai/api/mcp/v1/servers/ariunbolor/nsaf-mcp-server'

            If you have feedback or need assistance with the MCP directory API, please join our Discord server