Related MCP Server Resources

Explore more AI models, providers, and integration options:

  • Explore AI Models
  • Explore AI Providers
  • Explore MCP Servers
  • LangDB Pricing
  • Documentation
  • AI Industry Blog
  • doc-lib-mcp
  • TxtAi Memory Vector Server
  • AWS Knowledge Base Retrieval MCP Server
  • Perplexity AI MCP Server
  • Entscheidsuche MCP Server
Back to MCP Servers
Agentic AI with MCP

Agentic AI with MCP

Public
dev484p/AgenticAI_MCP

Connect a Groq-hosted LLM with Wikipedia, internet search, and financial data tools via a standardized Model Context Protocol server for dynamic, secure, and extensible AI-driven contextual information retrieval.

python
0 tools
May 30, 2025
Updated Jun 4, 2025

Supercharge Your AI with Agentic AI with MCP

MCP Server

Unlock the full potential of Agentic AI with MCP through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.

Unified API Access
Complete Tracing
Instant Setup
Get Started Now

Free tier available • No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests

Agentic AI with Model Context Protocol (MCP)

This project implements an Agentic AI system that connects a Groq-hosted LLM (qwen-qwq-32b model) with various tools through a custom Model Context Protocol (MCP) server. The system enhances the LLM's capabilities by providing contextual information from Wikipedia, internet search (via Tavily API), and financial data (via Yahoo Finance API).

About MCP

The Model Context Protocol (MCP) is an open standard developed by Anthropic to standardize how applications provide context to large language models (LLMs). It facilitates seamless integration between LLM applications and external data sources and tools, allowing AI systems to interact dynamically with various services through a standardized interface.

Key Features of MCP:

  • Standardization: Provides a universal protocol for interfacing AI assistants with structured tools and data layers.
  • Modular Architecture: Follows a client–server pattern over a persistent stream, typically mediated by a host AI system.
  • Dynamic Introspection: Supports dynamic discovery of tools and resources through methods like tools/list and resources/list.

Security: Incorporates host-mediated authentication and supports secure transport protocols.​ By adopting MCP, developers can build AI applications that are more interoperable, secure, and capable of complex workflows.​

To add new tools to the MCP server:​

  • Define the Tool: Create a new function that handles the specific task or data retrieval.​
  • Register the Tool: Update the server's tool registry to include the new function, specifying the tool's name and description.​
  • Handle Requests: Ensure the server can route incoming requests to the appropriate tool based on the query.​ This modular approach allows for easy expansion of the server's capabilities, enabling the language model to access a broader range of contextual information.

Features

  • MCP Server: Central hub that provides access to various tools
  • Three Integrated Tools:
    1. Wikipedia Search - for factual information retrieval
    2. Internet Search - powered by Tavily API for comprehensive web results
    3. Yahoo Finance API - for real-time stock and financial data
  • Groq API Integration: Ultra-fast LLM processing using qwen-qwq-32b model
  • Client-Server Architecture: Clean separation between tool management and LLM interaction

Prerequisites

Before you begin, ensure you have the following:

  • Install UV fro python installation
  • Groq API key. Refer to the documentation
  • Tavily API key (sign up at Tavily AI)

Installation

  1. Clone the repository:

    git clone https://github.com/dev484p/AgenticAI_MCP
    cd AgenticAI_MCP
    
  2. Install dependencies:

    uv add "mcp[cli]"
    
  3. Set up your environment variables: Update Groq and Tavily api key in keys.json

  4. Optional (To run the server with the MCP Inspector for development):

uv run mcp dev server.py
  1. Run the following command to initiate the chatbot:
    uv run client.py
    

Available Tools

The system provides three tools through the MCP server:

  1. Wiki Search:
  • Access Wikipedia information
  • Example query: "Tell me about the history of artificial intelligence"
  1. Internet Search (Tavily):
  • Get comprehensive web search results
  • Example query: "What are the latest developments in quantum computing?"
  1. Yahoo Finance:
  • Access stock prices and financial data
  • Example query: "What is the current price of AAPL stock?"

Refrence

  • https://modelcontextprotocol.io/introduction
  • https://github.com/langchain-ai/langchain-mcp-adapters
  • https://github.com/krishnaik06/MCP-CRASH-Course
Publicly Shared Threads0

Discover shared experiences

Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!

Share your threads to help others
Related MCPs5
  • doc-lib-mcp
    doc-lib-mcp

    Model Context Protocol server enabling document ingestion, chunking, semantic search, and advanced n...

    Added May 30, 2025
  • TxtAi Memory Vector Server
    TxtAi Memory Vector Server

    Model Context Protocol server offering advanced semantic search, persistent memory management, tag-b...

    Added May 30, 2025
  • AWS Knowledge Base Retrieval MCP Server
    AWS Knowledge Base Retrieval MCP Server

    Retrieval-Augmented Generation (RAG) server enabling efficient extraction of contextual information ...

    Added May 30, 2025
  • Perplexity AI MCP Server
    Perplexity AI MCP Server

    Provides seamless integration with Perplexity AI via Model Context Protocol, enabling chat, search, ...

    5 tools
    Added May 30, 2025
  • Entscheidsuche MCP Server
    Entscheidsuche MCP Server

    Provides standardized access to Swiss legal decisions via the Model Context Protocol, enabling searc...

    Added May 30, 2025