Skip to main content
Glama
Sign In
enesjakozh
Agentic AI with MCP

Agentic AI with MCP

by dev484p
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

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.

Related MCP server: Wikipedia MCP Server

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:

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

Available Tools

3 tools
internet_searchC

Search the internet using Tavily API.

Inputs: query (required), limit, include_raw_content.

wiki_searchC

Search Wikipedia for articles.

Inputs: query (required), limit.

yahoo_finance_searchC

Get stock information from Yahoo Finance.

Inputs: symbol (required), period.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.1/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: internet_search uses Tavily API for general web searches, wiki_search targets Wikipedia articles specifically, and yahoo_finance_search focuses on stock information from Yahoo Finance. There is no overlap in functionality or ambiguity between these three tools.

    Naming Consistency5/5

    All tool names follow a consistent snake_case pattern with a clear verb_noun structure: internet_search, wiki_search, and yahoo_finance_search. The naming is uniform and predictable across the entire set.

    Tool Count3/5

    With only 3 tools, the server feels thin for the broad domain implied by 'Agentic AI with MCP', which suggests a more comprehensive set of capabilities. While each tool is distinct, the count is borderline low for typical agentic AI tasks that might require more varied operations.

    Completeness2/5

    The tool surface is severely incomplete for an 'Agentic AI' server, as it only provides search functionalities without any CRUD operations, data processing, or other AI-related actions. There are significant gaps that will limit agent effectiveness, such as missing tools for data manipulation, analysis, or interaction with AI models.

    Resources

    Related MCP Connectors

    Related MCP Servers

    • StockFlow MCP Server

      twolven
      A
      license
      B
      quality
      C
      maintenance
      A Model Context Protocol server providing real-time stock data and options analysis through Yahoo Finance, enabling LLMs to access market data, analyze stocks, and evaluate options strategies.
      3
      27
      MIT

    • Wikipedia MCP Server

      Rudra-ravi
      A
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that retrieves information from Wikipedia to provide context to LLMs, allowing users to search articles, get summaries, full content, sections, and links from Wikipedia.
      22
      2,981 PyPI
      306
      MIT

    • MCP Yahoo Finance

      maxscheijen
      A
      license
      B
      quality
      B
      maintenance
      A Model Context Protocol server that enables interaction with Yahoo Finance to retrieve stock pricing, company information, and historical financial data through natural language queries.
      21
      1,006 PyPI
      29
      MIT

    • MCP Yahoo Finance

      marckwei
      A
      license
      C
      quality
      Not graded
      maintenance
      A Model Context Protocol server that provides tools for interacting with Yahoo Finance, allowing users to retrieve stock prices, company information, and perform financial data comparisons.
      11
      MIT

    Appeared in Searches