NSAF MCP Server
NSAF MCP 服务器
这是神经符号自主框架 (NSAF) 的模型上下文协议 (MCP) 服务器。它允许 AI 助手通过 MCP 协议与 NSAF 框架进行交互。
**注意:**此存储库包含 NSAF 框架代码和 MCP 服务器实现,使其成为可以在任何地方部署和使用的完整包。
**注意:**此实现使用了简化版的 MCP 协议,无需官方 MCP SDK。它实现了向 AI 助手公开 NSAF 功能所需的核心功能。
特征
使用可自定义的参数运行 NSAF 演进
比较不同的 NSAF 代理架构
将 NSAF 功能集成到 AI 助手中
Related MCP server: LLM Responses MCP Server
先决条件
Node.js 18+ 和 npm
安装了 NSAF 框架的 Python 3.8+
安装
克隆此存储库:
git clone https://github.com/ariunbolor/nsaf-mcp-server.git
cd nsaf-mcp-server安装依赖项:
npm install构建服务器:
npm run build配置
该服务器包含 NSAF 框架代码,因此基本使用无需额外配置。MCP 服务器设计为全局安装即可开箱即用。
用法
本地运行服务器
npm start部署到 GitHub
为您的 MCP 服务器创建一个新的 GitHub 存储库:
转到 GitHub 并创建一个名为
nsaf-mcp-server新存储库使用 README 文件初始化它
使用提供的安装脚本将您的代码推送到 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该脚本将:
如果需要,初始化 git
设置远程存储库
提交你的更改
尝试推送到 GitHub(带有处理现有存储库的选项)
为 CI/CD 配置 GitHub Actions(可选):
创建
.github/workflows目录添加用于测试和构建服务器的工作流文件
与人工智能助手一起使用
要将此 MCP 服务器与 Claude 等 AI 助手一起使用,您需要:
安装服务器:
选项 1:从 GitHub 安装(推送代码后):
npm install -g yourusername/nsaf-mcp-server选项 2:从本地目录安装:
# 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 .将服务器添加到您的 MCP 设置配置中:
对于 Claude Desktop 应用程序,编辑~/Library/Application Support/Claude/claude_desktop_config.json (在 macOS 上):
{
"mcpServers": {
"nsaf": {
"command": "nsaf-mcp-server",
"args": [],
"env": {},
"disabled": false,
"autoApprove": []
}
}
}对于 Cline,编辑/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": []
}
}
}可用工具
运行_nsaf_evolution
使用指定的参数运行 NSAF 演进。
参数:
population_size:代理人口规模(默认值:20)generations:进化的代数(默认值:10)mutation_rate:突变率(0.0-1.0)(默认值:0.2)crossover_rate:交叉率(0.0-1.0)(默认值:0.7)architecture_complexity:代理架构的复杂性(“简单”,“中等”,“复杂”)(默认值:“中等”)
比较nsaf代理
比较不同的 NSAF 代理架构。
参数:
architectures:要比较的架构列表(默认值:['简单','中等','复杂'])
执照
麻省理工学院
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Flicense-qualityDmaintenanceA versatile Model Context Protocol server that enables AI assistants to manage calendars, track tasks, handle emails, search the web, and control smart home devices.23
- Alicense-qualityDmaintenanceA Model Context Protocol server that enables collaborative debates between multiple AI agents, allowing them to discuss and reach consensus on user prompts.1MIT
- AlicenseBqualityCmaintenanceA 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.9132MIT
- Alicense-qualityCmaintenanceA Model Context Protocol server that connects AI assistants with the Kernel platform, enabling them to deploy applications, automate web browsers, and manage cloud resources.31MIT
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal E…
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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