Understand the code.
Keep the context small.
Ask about a highlight, a few lines, a file, or a folder. Give your existing AI model precise AST evidence and a product-level point of view.
No sign-in. No extra API key. No personal uploads.
One prompt. Real tool output.
Two small source files: one calculates a paid-order total; one builds the report. Choose an example to make a real MCP call. This page shows the evidence; your AI client supplies the conversational answer.
Inspect the exact tool response
Connect once. Ask naturally.
Add this Streamable HTTP server in an MCP-compatible AI client. It exposes the same public example data as the demo above. Your normal AI account and usage apply.
https://site--codearchitect--74wvcb9qzxr6.code.run/mcp/codearchitect/serverExample HTTP configuration
{
"servers": {
"codearchitect": {
"type": "http",
"url": "https://site--codearchitect--74wvcb9qzxr6.code.run/mcp/codearchitect/server"
}
}
}Other clients may use a different configuration format. Choose HTTP / Streamable HTTP and paste the endpoint above. No authorization header is required.
Bring the tools to your own work.
Your selected source folder. No generated summaries or model calls on the server.
npx --yes --package https://site--codearchitect--74wvcb9qzxr6.code.run/mcp/install/codearchitect-mcp-0.2.0.tgz codearchitect-mcp --project-root /absolute/path/to/project
Requires Node.js 20+ · npm / npx.
Add this command as a local stdio MCP server in your AI app. Replace the example path with a project folder. In Git repositories, source reads are limited to tracked files.
Download the versioned install package ↗What “local” means for privacy
These MCP tools do not save request or response content, enable telemetry, or call a model provider. They return selected evidence to your AI host. That host may retain it or send it to its model provider under its own policy.
CodeArchitect reads supported source files inside the project folder you select. It does not execute that code or write the source/AST context to a disk cache.