mcpField
S
Scast

Scast

Local
davidkingzyb.github.ioDeveloper Tools39Updated 25w ago
RepositoryVisit website

About Scast

SCAST is a static code analysis and visualization tool that converts code into UML diagrams and flowcharts. It is aimed at developers who need to understand code structure quickly, and it can also run as an MCP server inside an AI client.

Key features

  1. 01Parse code into an AST for static analysis
  2. 02Generate UML, AST tree and Mermaid flowcharts
  3. 03Support C#, JavaScript, Python, TypeScript, C and C++
  4. 04Extend to other languages via TreeSitter

Use cases

  1. 01Generate UML diagrams to understand an unfamiliar codebase
  2. 02Locate the source of a class, method or field definition
  3. 03Pass analysis results to an AI client for explanation

MCP support

This project can run as an MCP server, providing the scast_analysis and scast_retriever tools to MCP clients for code analysis and definition retrieval.

#scast#static-code-analysis#visualization

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

🔱SCAST

Static Code Analysis and Visualization

2026/3/6 by DKZ

README image

English/中文

🔱SCAST is a programmatic tool that converts code into UML diagrams and flowcharts.

📽️watch video
📽️Tutorial
📽️MCP

support language

  • csharp
  • javascript
  • python
  • typescript
  • c
  • cpp
  • use TreeSitter you can find more language or customize your language.

The underlying principle involves leveraging a parser to parse the code into an Abstract Syntax Tree (AST), followed by static analysis, and finally utilizing Mermaid and D3 for visualization.

You can try it online or just download this repo and open SCAST.html with browser.
For Developers it can be deployed on servers using npm run server. Or use it as MCP server integrate it into your AI client.

scast_uml

MCP

mcp

  1. git clone https://github.com/davidkingzyb/SCAST.git download the source code.
  2. npm install
  3. config at your client
{
  "mcpServers": {
    "scast":{
      "command":"node",
      "args":[
        "/YOUR_INSTALL_DIR/SCAST/mcp/index.js",
        "/YOUR_WORKSPACE/",
        "C:\\Users\\DKZ\\OTHER_ALLOWED_DIR\\",
      ]
    }
  }
}
Tools
scast_analysis:

SCAST is a tool designed to assist users in analyzing and summarizing code through visualization. By simply providing the folder path where the code is located, SCAST can perform static analysis on the code, generating an AST tree to helping users understand the code structure and explain its functionality. Generate various visual charts such as UML diagrams, AST tree diagrams and Mermaid flowcharts. Finally return a keyword list containing all class and method names along with their functionality explanations, and include a link to allow users to view the chart details in their browser.

scast_retriever

SCAST is a tool that helps users analyze and summarize code and provides visualizations. You need to provide the file path of the source code folder. SCAST will perform static analysis on the source codes in the folder, generating an AST tree to help users understand the code structure and explain its functionality. After analyzing the code directory with SCAST, you can use keywords in the AST tree for searching, better answering user questions using a RAG method. This keyword can be a class name, method name, or field name. SCAST will find the source code at its definition and return it.

Ollama AI

install ollama first
see ai.js for more details

ollama

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.