• INVENTORY
  • VERSIONING
  • CONTEXT
  • REVIEW

How to map tech stack usage with your AI

Connect GitHub Market Intelligence to your AI client. Once connected, your agent can inspect codebases to pull out exact dependency lists and framework versions.

Ask AI about this page

Short answer

How can I see what libraries and frameworks a repo uses?

Your AI scans the source code and documentation to identify every dependency and framework in a project. You'll get a clear breakdown of the actual tech stack being used.

Tech stack outcomes

What you'll discover

The AI turns raw code into organized stack profiles.

INVENTORY

Dependency lists

The AI identifies every library and package used in a project. You get a clean list of what's actually running in the code.

VERSIONING

Framework versions

It detects specific versions of frameworks like React or Django. This helps you spot outdated or incompatible tools.

CONTEXT

Project intent

By reading documentation, the AI understands why certain tools were chosen. You get the reasoning behind the architecture.

REVIEW

Human validation

The AI flags potential mismatches or missing files. You decide if the detected stack matches your project requirements.

The workflow

What your AI does when the request arrives.

The AI moves from high-level documentation to deep code inspection to build a complete profile.

  1. Read documentation

    The AI starts by looking at the project's README to understand the intended setup and primary technologies.

    get_repo_readme

  2. Scan dependencies

    It looks through the codebase to find specific imports and package files used by the project.

    search_code_usage

  3. Build stack profile

    The AI aggregates all found libraries and frameworks into a single, coherent tech stack report.

    analyze_tech_stack

  4. Verify usage

    The agent double-checks the code to ensure the identified libraries are actually being called in the logic.

    search_code_usage

Try it

Copy these to start.

Use these prompts to trigger the analysis immediately.

Starting points

Swap the repository names for the actual GitHub URLs you want to analyze.

GitHub Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_09VN4PRjttqUr5AJVJeakra5JvHOVxjxe9UF08Zc/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — GitHub capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "github-market-intelligence-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_09VN4PRjttqUr5AJVJeakra5JvHOVxjxe9UF08Zc/mcp"
    }
  }
}
Copy into chat04

  • Analyze the tech stack for the repository https://github.com/facebook/react.

  • What specific versions of dependencies are being used in the kubernetes/kubernetes repo?

  • Check the README and code for the pytorch/pytorch project to list all major frameworks used.

  • Identify all Python libraries used in the pandas-dev/pandas repository.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect GitHub Market Intelligence once, then ask.

Click the link to connect your account. Your credentials stay encrypted, and you can start asking questions in your preferred AI client right away.

Connect GitHub Market Intelligence to your AI

FAQ

How this task behaves

  • 01

    Can the AI change my code or dependencies?

    No. The AI only reads and analyzes the code. It cannot push changes, commit code, or modify your repositories.

  • 02

    Does the AI need permission to see private repos?

    Yes. The AI can only access repositories that your connected GitHub account has permission to view.

  • 03

    Can it find libraries that aren't explicitly listed in a package file?

    Yes, because it uses code analysis to find actual imports and usage in the source files.

  • 04

    Will the AI delete any files in my repository?

    No. This MCP is read-only. It has no capability to delete, move, or rename files.

  • 05

    Can it analyze a repository if I only provide a URL?

    Yes, as long as the repository is public or your GitHub connection has access to it.

  • More questions about GitHub Market Intelligence? The Connector page answers them. See everything the GitHub Market Intelligence Connector can do

Connect GitHub to Claude, Cursor, ChatGPT & more