MCP Learning Series - Part 5

-

 


We know that MCP is a Client-Server Architecture. Both the sides offer services to each other. From the server side it offers 3 different services (Primitive) to the client.

1) Tools - Used by the LLM
2) Resources - Used by the AI Applications
3) Prompts -  Used by the users interacting with the AI Applications

Tools @mcp.tool() - These are the functions used by the LLM's to perform an action.
Resources @mcp.resource() - Refers to any data sources which is access by the AI application including reading file, accessing the database via SQL, reading a CSV file or connecting to a DataLake.
Prompts @mcp.prompt() -  Structured template which gets inputs from the user and perform an action.

How to add a prompt and resources to existing MCP Server:

@mcp.prompt()
def get_prompt(topic: str) -> str:
    """
    Returns a prompt for the given topic which will do a detailed analysis on the topic.
    Args:
        topic (str): The topic to analyze.
    """
    return (
        f"Do a comprehensive, detailed analysis on the topic of {topic}. and provide "
        f"a summary of the key points. "
        "The analysis should be thorough and cover all relevant aspects of the topic. "
        "The summary should be concise and highlight the most important findings. "
    )

This prompt takes an input on a topic and uses AI application (LLM) to return the data with detailed analysis.

Let's see how this prompt works with Claude:





Above is the response from Claude for the given input prompt.

Let's add resource: I am using a Dictionary with dummy library data as resource.
LIBRARY_DATA = {
    "books": [
        {
            "id": "B001",
            "title": "Artificial Intelligence: A Modern Approach",
            "authors": ["Stuart Russell", "Peter Norvig"],
            "isbn": "978-0134610993",
            "category": "Computer Science",
            "publisher": "Pearson",
            "publication_year": 2020,
            "copies_total": 5,
            "copies_available": 2,
            "location": "CS-Section-A-Shelf-12",
            "status": "available",
            "last_updated": "2024-01-15T10:30:00Z",
        },
        {
            "id": "B002",
            "title": "Clean Code: A Handbook of Agile Software Craftsmanship",
            "authors": ["Robert C. Martin"],
            "isbn": "978-0132350884",
            "category": "Software Engineering",
            "publisher": "Prentice Hall",
            "publication_year": 2008,
            "copies_total": 3,
            "copies_available": 0,
            "location": "SE-Section-B-Shelf-05",
            "status": "checked_out",
            "last_updated": "2024-01-20T14:15:00Z",
        }
    ]
}

@mcp.resource("library://catalog")
def get_full_catalog() -> str:
    """
    Returns the complete library catalog with all books and their detailed information.
    """
    try:
        books = LIBRARY_DATA["books"]
        catalog = {
            "total_books": len(books),
            "last_updated": datetime.now().isoformat(),
            "books": books,
        }

        return json.dumps(catalog, indent=2)

    except Exception as e:

        return json.dumps({"error": str(e)})

Testing with Claude:

We used the resource "get_full_catalog" to list of books from the catalog.










Comments

Post a Comment

Popular posts from this blog

Agentic AI - Series 3

-
Image
                                                                      In this blog we will see how to build a simple agent without using any LLM model. Simple flow of an agent: Agent takes input -> Based on the input, it decides which tool to use -> Performs operation and send the output back to the user. An AI agent framework is  a set of tools, libraries, and structures that simplifies building, deploying, and managing autonomous AI agents. But, here we are going to build an agent without using any framework and LLM's. Agent functionality is to perform "Addition" and "Subtraction". Agent uses 2 python functions (Tools) to perform addition and subtraction operations. Finally, it send the output to the user. We are going to implement the above discussed functionality vi...
Read more

Principal SRE - Interview Question

-
Image
  Sharing some of the interview questions for the role of Principal SRE from Apple: 1) Tell me about a production outage you’ve handled that had ambiguous symptoms. How did you narrow it down? 2) How do you decide what belongs in an SLO, and how do you avoid overengineering it? 3) You inherit a platform with strong uptime but high operational toil. What do you change first? 4) How do you handle a disagreement with product leadership when reliability work competes with feature delivery? 5) A service is scaling rapidly and latency is degrading under load. Walk me through your approach. 6) What does “good observability” mean to you in practice? 7) Describe how you would lead a major incident. 8) What’s your philosophy on automation in production operations? 9) How do you evaluate whether an architecture is resilient enough? 10) You’re the on-call SRE for a globally used service. At 2:00 AM, error rates jump from 0.2% to 8%, latency doubles, and one region is still healthy wh...
Read more

Agentic AI - Series 4

-
Image
                                                                   In this blog, will how to create a simple agent using AI framework like Langchain with a simple LLM model  gpt-4o-mini. from langchain_openai import ChatOpenAI from langchain_core . tools import tool import os # Creating a tool @ tool def add_numbers ( x : int , y : int ) -> int :     "Add two numbers"     return x + y @tool is a decorator to define a tool. This is a simple tool to add 2 numbers. The below line creates a Langchain LLM wrapper around on the OpenAI chat mode 'gpt-4o-mini' # Binding the tool to a model llm = ChatOpenAI( model = "gpt-4o-mini" ).bind_tools([add_numbers]) response = llm .invoke( "What is 5 + 7?" ) When we print response, is the expected outcome? Is it 12. NO...
Read more