vguhesan

MCP Server/Client as a proxy to existing Java Spring REST API

In this example, we will build a MCP Server/Client as a proxy to existing Java Spring REST API.

Assume an existing Spring Boot REST API app with a ProductController exposing /products endpoints. We'll add MCP support using Spring AI.

1. Add Dependencies (pom.xml):

vguhesan

// Filename: McpServerApp.java
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;
import org.springframework.context.annotation.Bean;
import org.springframework.web.client.RestTemplate;
import java.util.List;
import org.springframework.ai.mcp.Tool;
import org.springframework.ai.mcp.ToolCallbacks;

@SpringBootApplication

vguhesan

MCP Server + Client Example (leveraging existing REST APIs)

To expose existing Python code as an MCP server, use fastMCP's decorators to annotate functions as tools or resources. This involves:

• Wrapping existing functions with @mcp.tool for executable actions or @mcp.resource for data access.
• Adding type hints and docstrings for automatic schema generation.
• Handling context if needed (e.g., for logging or nested calls).

Assume existing code in existing_math.py with functions subtract and get_pi. (see file)

vguhesan

MCP Server & Client Python Example Using fastMCP Framework

In this example, we will be creating an example of a MCP Server & Client Python Example Using fastMCP Framework

fastMCP is a popular Python framework for building MCP servers and clients. It abstracts protocol details, allowing focus on logic via decorators like @tool and @resource. Below are step-by-step examples with full, working code.

MCP Server in Python Using fastMCP

vguhesan

RAG Implementation using LangChain, OpenAI, with ChromaDB or SingleStore

(LangChain, OpenAI, with ChromaDB or SingleStore)

This solutioning requires internet and API access to tools and services externally

A simple RAG system over a text document using LangChain, OpenAI for embeddings/LLM, and Chroma as the vector DB.

Prerequisites

Install packages

vguhesan

RAG Implementation

No Public API Services required

Locally Running LLM Model

This is a RAG implementation example with no internet based API or tools.

Single-file RAG pipeline using:

• LlamaIndex (open source)
• Local Ollama (llama3 for both embeddings + generation)
• SingleStore DB (local vector store)

vguhesan

// ==UserScript==
// @name         Grok Wide Output Results Panel
// @namespace    http://digitalriver.blog/grok-wide-output
// @version      2026-02-16
// @description  Makes the Grok Results Output be wider
// @author       Venkatt Guhesan
// @match        https://grok.com/
// @icon         https://grok.com/images/favicon.ico
// @grant        none
// ==/UserScript==

vguhesan

// Run me in a developer JavaScript Console
// Need to place this in a TamperMonkey UserScripts soon

var targetElem = document.querySelector('html > body > div:nth-of-type(2) > div:nth-of-type(2) > div > div > main > div:nth-of-type(2)');
targetElem.style.setProperty("--content-max-width", "70rem");

vguhesan

#!/bin/bash

# Delete all node_modules directories recursively
find . -type d -name "node_modules" -print0 | xargs -0 rm -rf

echo "All node_modules directories deleted."

vguhesan

du -sh * | sort -h | tail -n 10