Introduction
in September 2025, I took half in a hackathon organized by Mistral in Paris. All of the groups needed to create an MCP server and combine it into Mistral.
Although my staff didn’t win something, it was a unbelievable private expertise! Moreover, I had by no means created an MCP server earlier than, so it allowed me to achieve direct expertise with new applied sciences.
Because of this, we created Prédictif — an MCP server permitting to coach and take a look at machine studying fashions immediately within the chat and persist saved datasets, outcomes and fashions throughout completely different conversations.
On condition that I actually loved the occasion, I made a decision to take it a step additional and write this text to offer different engineers with a easy introduction to MCP and in addition provide a information on creating an MCP server from scratch.
If you’re curious, the hackathon’s options from all groups are right here.
MCP
AI brokers and MCP servers are comparatively new applied sciences which are presently in excessive demand within the machine studying world.
MCP stands for “Mannequin Context Protocol” and was initially developed in 2024 by Anthropic after which open-sourced. The motivation for creating MCP was the truth that completely different LLM distributors (OpenAI, Google, Mistral, and so on.) supplied completely different APIs for creating exterior instruments (connectors) for his or her LLMs.
Because of this, if a developer created a connector for OpenAI, then they must carry out one other integration in the event that they needed to plug it in for Mistral and so forth. This method didn’t permit the easy reuse of connectors. That’s the place MCP stepped in.
With MCP, builders can create a software and reuse it throughout a number of MCP-compatible LLMs. It ends in a a lot less complicated workflow for builders as they not have to carry out extra integrations. The identical is appropriate with many LLMs.
For info, MCP makes use of JSON-RPC protocol.
Instance
Step 1
We’re going to construct a quite simple MCP server that may have just one software, whose objective can be to greet the consumer. For that, we’re going to use FastMCP — a library that permits us to construct MCP servers in a Pythonic approach.
To start with, we have to setup the setting:
uv init hello-mcp
cd hello-mcpAdd a fastmcp dependency (this may replace the pyproject.toml file):
uv add fastmcpCreate a important.py file and put the next code there:
from mcp.server.fastmcp import FastMCP
from pydantic import Subject
mcp = FastMCP(
identify="Good day MCP Server",
host="0.0.0.0",
port=3000,
stateless_http=True,
debug=False,
)
@mcp.software(
title="Welcome a consumer",
description="Return a pleasant welcome message for the consumer.",
)
def welcome(
identify: str = Subject(description="Title of the consumer")
) -> str:
return f"Welcome {identify} from this superb software!"
if __name__ == "__main__":
mcp.run(transport="streamable-http")Nice! Now the MCP server is full and might even be deployed regionally:
uv run python important.pyAny further, create a GitHub repository and push the native venture listing there.
Step 2
Our MCP server is prepared, however shouldn’t be deployed. For deployment, we’re going to use Alpic — a platform that permits us to deploy MCP servers in actually a number of clicks. For that, create an account and sign up to Alpic.
Within the menu, select an choice to create a brand new venture. Alpic proposes to import an present Git repository. If you happen to join your GitHub account to Alpic, you need to have the ability to see the record of obtainable repositories that can be utilized for deployment. Choose the one equivalent to the MCP server and click on “Import”.
Within the following window, Alpic proposes a number of choices to configure the setting. For our instance, you may go away these choices by default and click on “Deploy”.
After that, Alpic will assemble a Docker container with the imported repository. Relying on the complexity, deployment could take a while. If every little thing goes effectively, you will notice the “Deployed” standing with a inexperienced circle close to it.
Beneath the label “Area”, there’s a JSON-RPC tackle of the deployed server. Copy it for now, as we might want to join it within the subsequent step.
Step 3
The MCP server is constructed. Now we have to join it to the LLM supplier in order that we will use it in conversations. In our instance, we’ll use Mistral, however the connection course of needs to be related for different LLM suppliers.
Within the left menu, choose the “Connectors” possibility, which can open a brand new window with obtainable connectors. Connectors allow LLMs to hook up with MCP servers. For instance, in the event you add a GitHub connector to Mistral, then within the chat, if wanted, LLM will have the ability to search code in your repositories to offer a solution to a given immediate.
In our case, we wish to import a customized MCP server we’ve got simply constructed, so we click on on the “Add connector” button.
Within the modal window, navigate to “Customized MVP Connector” and fill within the obligatory info as proven within the screenshot under. For the connector server, use the HTTPS tackle of the deployed MCP server in step 2.
After the connector is added, you may see it within the connectors’ menu:
If you happen to click on on the MCP connector, within the “Features” subwindow, you will notice an inventory of applied instruments within the MCP server. In our instance, we’ve got solely applied a single software “Welcome”, so it’s the solely operate we see right here.
Step 4
Now, return to the chat and click on the “Allow instruments” button, which lets you specify the instruments or MCP servers the LLM is permitted to make use of.
Click on on the checkbox equivalent to our connector.
Now it’s time to take a look at the connector. We are able to ask the LLM to make use of the “Welcome” software to greet the consumer. In Mistral chat, if the LLM acknowledges that it wants to make use of an exterior software, a modal window seems, displaying the software identify (“Welcome”) and the arguments it’ll take (identify = “Francisco”).
To substantiate the selection, click on on “Proceed”. In that case, we’ll get a response:
Glorious! Our MCP server is working accurately. Equally, we will create extra advanced instruments.
Conclusion
On this article, we introduce MCP as an environment friendly mechanism for creating connectors with LLM distributors. Its simplicity and reusability have made MCP very talked-about these days, permitting builders to cut back the time required to implement LLM plugins.
Moreover, we’ve got examined a easy instance that demonstrates how one can create an MCP server. In actuality, nothing prevents builders from constructing extra superior MCP purposes and leveraging extra performance from LLM suppliers.
For instance, within the case of Mistral, MCP servers can make the most of the performance of Libraries and Paperwork, permitting instruments to take as enter not solely textual content prompts but in addition uploaded information. These outcomes might be saved within the chat and made persistent throughout completely different conversations.
Assets
All photos until in any other case famous are by the writer.
