napi - Better Software Architecture for the AI Age MCP Server

@nanoapi-io

代码仓库主页

基本信息

分类

其他

许可证

NOASSERTION

传输方式

stdio

作者

nanoapi-io

关于 napi - Better Software Architecture for the AI Age MCP Server

Software architecture tooling for the AI age

#refactoring #python #java #cli #php #node #microservices #ai #csharp #devtools #code-analysis #apis#monolith#code-visualization#system-design#source-code-analysis#live-documentation#software-modernization#legacy-code-refactoring#mcp-server

napi - Better Software Architecture for the AI Age MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "napi": {
      "command": "deno",
      "args": [
        "task",
        "dev"
      ]
    }
  }
}

napi - Better Software Architecture for the AI Age MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is napi?

napi is a fully offline CLI that analyzes your codebase's architecture—dependencies, complexity, and structure—then lets you visualize and refactor it, all without sending your code anywhere. It generates dependency manifests from source code, stores them locally, and serves an interactive graph visualizer directly from the CLI.

How to use napi?

Install on Unix via curl -fsSL https://raw.githubusercontent.com/nanoapi-io/napi/refs/heads/main/install_scripts/install.sh | bash or download a binary from GitHub Releases. Use napi init to create a configuration, napi generate to produce a dependency manifest, and napi view to open an interactive visualizer in your browser.

Key features of napi

Dependency analysis mapping every file, symbol, and dependency automatically.
Audit detection for files exceeding complexity, size, or coupling thresholds.
Interactive visualizer using Cytoscape.js graphs served locally in your browser.
Symbol extraction of functions, classes, or symbols into standalone files.
Optional AI labeling with OpenAI, Google, or Anthropic models.
Fully offline operation with no accounts, servers, or data leaving your machine.

Use cases of napi

Understand and visualize your codebase’s architecture to plan refactoring.
Track dependency changes over time by generating manifests on every push.
Extract complex symbols into separate files to reduce coupling.
Enforce architecture quality gates in CI/CD pipelines.

常见问题

Does napi send my code anywhere?

No. napi is fully offline—it never sends your code to any server. All processing happens locally on your machine.

Which programming languages does napi support?

Python, C#, C, and Java are currently supported. Support for C++, PHP, and JavaScript/TypeScript is in progress.

Where are dependency manifests stored?

Manifests are saved as JSON files in `.napi/manifests/` relative to your project root. Each manifest contains branch, commit SHA, and timestamp metadata.

Can napi be used in CI/CD?

Yes. napi can generate manifests non-interactively using `--branch`, `--commit-sha`, and `--commit-sha-date` options. The README includes a GitHub Actions workflow example.

How do I enable AI labeling for dependencies?

Run `napi set apiKey` and follow the prompts to configure an API key for Google, OpenAI, or Anthropic. Labeling settings are stored globally in your OS config directory.

其他分类下的更多 MCP 服务器

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K