azure-multi-mcp-starter
This project is a starter template for building Model Context Protocol (MCP) agents using Azure OpenAI, not OpenAI. It demonstrates how to use the MCP protocol with Azure's hosted models, providing a foundation for developing advanced AI agents that can interact with external tools and services.
What is MCP?
Model Context Protocol (MCP) is an open protocol that standardizes how language models interact with external tools, APIs, and environments. MCP enables models to call functions, access data, and perform actions beyond simple text generation, making them more useful and interactive in real-world applications.
LangChain MCP Adapter
The LangChain MCP adapter is a library that bridges LangChain agents with MCP servers. It allows you to use LangChain's agent framework to communicate with any MCP-compliant server, enabling seamless integration of tool use, function calling, and advanced agent behaviors.
MCP Options
There are several MCP server implementations and options available:
- Python MCP Server: Run your own MCP server in Python, customizing tool support and logic.
- LangChain MCP Adapter: Use LangChain's adapter to connect agents to MCP servers.
About This Template
This repository is designed as a quick-start template for developers building MCP agents with specifically Azure OpenAI, as other guides only provided template for OpenAI endpoints. It includes sample code for connecting to an MCP server, using the LangChain MCP adapter, and running an agent that can interact with external tools. You can create your own sample MCP Server with MCP tools for your AI to perform agentic actions. It is intended for Azure OpenAI users and requires adaptation to work with OpenAI's public API.
Quickstart
To run this template follow the steps:
- Clone repository
- ```` pip install -r requirements.txt ```
- Populate your .env file with the following: AZURE_OPENAI_API_KEY, AZURE_OPENAI_ENDPOINT,AZURE_OPENAI_VERSION
- In terminal, run
python frontend_api.py - This will start all the MCP servers and the LangChain MCP adapter.
Sample application
Upcoming features
Include more baseline MCP server integration with Azure AI Foundry, Azure MCP, Fabric MCP Server
For more information, see the official documentation for MCP, LangChain, and Azure OpenAI.
1 maintainer
Metadata
1 maintainer
Release files for iflow-mcp_delynchoong-azure-openai-agent-multi-mcp-starter 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| iflow_mcp_delynchoong_azure_openai_agent_multi_mcp_starter-0.1.0.tar.gz | 130.1 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| iflow_mcp_delynchoong_azure_openai_agent_multi_mcp_starter-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 137.7 kB
Release files / iflow_mcp_delynchoong_azure_openai_agent_multi_mcp_starter-0.1.0.tar.gz
| Download URL | iflow_mcp_delynchoong_azure_openai_agent_multi_mcp_starter-0.1.0.tar.gz |
|---|---|
| Size | 130.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
836f2dbda6a9b05d9d26c021a72fa610f5f878d0891863f6e97379579a7c3731
|
|
BLAKE2b-256 checksum How to use checksums |
f8557cc7a8c59518078d9fd0271e8085a0dfb578ed7a58ce1eaa407c9d811c99
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.2 {"installer":{"name":"uv","version":"0.10.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / iflow_mcp_delynchoong_azure_openai_agent_multi_mcp_starter-0.1.0-py3-none-any.whl
| Download URL | iflow_mcp_delynchoong_azure_openai_agent_multi_mcp_starter-0.1.0-py3-none-any.whl |
|---|---|
| Size | 7.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
dd8d299e956962c376d66e294f4605afd167e123d851291567cb6de76c67a3ac
|
|
BLAKE2b-256 checksum How to use checksums |
33538cd60c4688108e6dd64818d8ad20008140fb8ef498b1154abfa255dd61ed
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.2 {"installer":{"name":"uv","version":"0.10.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
