Skip to main contentSkip to footer
ExamplescriptadvancedRunnableguided-flow

Client Simple

Runnable example (advanced) for script using mcp, openai.

Key Facts

Level
advanced
Runtime
Python • OpenAI API
Pattern
Inspectable flow with visible system boundaries
Interaction
Live sandbox • Script
Updated
14 March 2026

Navigate this example

High-level flow

How this example moves from input to execution and reviewable output
Client Simple -> Load environment keys -> Send chat request -> Send message payload -> Expose MCP tools -> Render the visible result

Start

Client Simple

Checkpoint

Load environment keys

Outcome

Send chat request

Why this page exists

This example is shown as both real source code and a product-facing interaction pattern so learners can connect implementation, UX, and doctrine without leaving the library.

Visual flowReal sourceSandbox or walkthroughMCP access
How should this example be used in the platform?

Use the sandbox to understand the experience pattern first, then inspect the source to see how the product boundary, model boundary, and doctrine boundary are actually implemented.

UX pattern: Inspectable flow with visible system boundaries
Expose meaningful operational state, not internal complexity
Establish trust through inspectability
Make hand-offs, approvals, and blockers explicit
Source references
Library entry
mcp-crash-course-4-openai-integration-client-simple
Source path
content/example-library/sources/mcp/crash-course/4-openai-integration/client-simple.py
Libraries
mcp, openai, python-dotenv
Runtime requirements
OPENAI_API_KEY
Related principles
Expose meaningful operational state, not internal complexity, Establish trust through inspectability, Make hand-offs, approvals, and blockers explicit, Represent delegated work as a system, not merely as a conversation

client-simple.py

python
import asyncio
import json
from contextlib import AsyncExitStack
from typing import Any, Dict, List

import nest_asyncio
from dotenv import load_dotenv
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client
from openai import AsyncOpenAI

# Apply nest_asyncio to allow nested event loops (needed for Jupyter/IPython)
nest_asyncio.apply()

# Load environment variables
load_dotenv("../.env")

# Global variables to store session state
session = None
exit_stack = AsyncExitStack()
openai_client = AsyncOpenAI()
model = "gpt-4o"
stdio = None
write = None


async def connect_to_server(server_script_path: str = "server.py"):
    """Connect to an MCP server.

    Args:
        server_script_path: Path to the server script.
    """
    global session, stdio, write, exit_stack

    # Server configuration
    server_params = StdioServerParameters(
        command="python",
        args=[server_script_path],
    )

    # Connect to the server
    stdio_transport = await exit_stack.enter_async_context(stdio_client(server_params))
    stdio, write = stdio_transport
    session = await exit_stack.enter_async_context(ClientSession(stdio, write))

    # Initialize the connection
    await session.initialize()

    # List available tools
    tools_result = await session.list_tools()
    print("\nConnected to server with tools:")
    for tool in tools_result.tools:
        print(f"  - {tool.name}: {tool.description}")


async def get_mcp_tools() -> List[Dict[str, Any]]:
    """Get available tools from the MCP server in OpenAI format.

    Returns:
        A list of tools in OpenAI format.
    """
    global session

    tools_result = await session.list_tools()
    return [
        {
            "type": "function",
            "function": {
                "name": tool.name,
                "description": tool.description,
                "parameters": tool.inputSchema,
            },
        }
        for tool in tools_result.tools
    ]


async def process_query(query: str) -> str:
    """Process a query using OpenAI and available MCP tools.

    Args:
        query: The user query.

    Returns:
        The response from OpenAI.
    """
    global session, openai_client, model

    # Get available tools
    tools = await get_mcp_tools()

    # Initial OpenAI API call
    response = await openai_client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": query}],
        tools=tools,
        tool_choice="auto",
    )

    # Get assistant's response
    assistant_message = response.choices[0].message

    # Initialize conversation with user query and assistant response
    messages = [
        {"role": "user", "content": query},
        assistant_message,
    ]

    # Handle tool calls if present
    if assistant_message.tool_calls:
        # Process each tool call
        for tool_call in assistant_message.tool_calls:
            # Execute tool call
            result = await session.call_tool(
                tool_call.function.name,
                arguments=json.loads(tool_call.function.arguments),
            )

            # Add tool response to conversation
            messages.append(
                {
                    "role": "tool",
                    "tool_call_id": tool_call.id,
                    "content": result.content[0].text,
                }
            )

        # Get final response from OpenAI with tool results
        final_response = await openai_client.chat.completions.create(
            model=model,
            messages=messages,
            tools=tools,
            tool_choice="none",  # Don't allow more tool calls
        )

        return final_response.choices[0].message.content

    # No tool calls, just return the direct response
    return assistant_message.content


async def cleanup():
    """Clean up resources."""
    global exit_stack
    await exit_stack.aclose()


async def main():
    """Main entry point for the client."""
    await connect_to_server("server.py")

    # Example: Ask about company vacation policy
    query = "What is our company's vacation policy?"
    print(f"\nQuery: {query}")

    response = await process_query(query)
    print(f"\nResponse: {response}")

    await cleanup()


if __name__ == "__main__":
    asyncio.run(main())
What should the learner inspect in the code?

Look for the exact place where system scope is bounded: schema definitions, prompt framing, runtime configuration, and the call site that turns user intent into a concrete model or workflow action.

Look for output contracts and validation
Look for the exact execution call
Look for what the product could expose to the user
How does the sandbox relate to the source?

The sandbox should make the UX legible: what the user sees, what the system is deciding, and how the result becomes reviewable. The source then shows how that behavior is actually implemented.

Read the implementation summary.
Step through the user and system states.
Inspect the source code with the highlighted doctrine decisions in mind.
SandboxInspectable flow with visible system boundaries
Interaction walkthrough

Use the sandbox to step through the user-visible experience, the system work behind it, and the doctrine choice the example is making.

UX explanation

The sandbox explains what the user should see, what the system is doing, and where control or inspectability must remain explicit.

AI design explanation

The page turns raw source into a product-facing pattern: what the model is allowed to decide, what the product should expose, and where deterministic code or review should take over.

Interaction walkthrough

  1. 1Read the implementation summary.
  2. 2Step through the user and system states.
  3. 3Inspect the source code with the highlighted doctrine decisions in mind.

Visible to the user

A script demonstrating mcp + openai.

System work

The product prepares a bounded model or workflow task.

Why it matters

The interface should make the delegated task legible before automation happens.

Used in courses and paths

This example currently stands on its own in the library, but it still connects to the principle system and the broader example family.

Related principles

Runtime architecture

Use this example in your agents

This example is also available through the blueprint’s agent-ready layer. Use the For agents page for the public MCP, deterministic exports, and Claude/Cursor setup.

Define triggers, context, and boundaries before increasing autonomy
Make control, observability, and recovery explicit in the runtime
Choose the right operational patterns before delegating to workflows