page_type: sample languages:

• python products:
• azure-openai
• azure-container-apps
• azure
• langchain
• pgvector urlFragment: langchain-agent-python name: LangChain Sales Agent with MCP and Azure OpenAI (Python) description: A multi-step LangChain v1 sales-conversation agent that uses the Azure OpenAI Responses API, an MCP server with Postgres + pgvector for catalog and CRM tools, and ships with one command via azd up.

LangChain Sales Agent (Responses API + MCP)

A Python sample that shows how to build a multi-step sales agent with LangChain v1 and Azure OpenAI that drive sales through a 6-step funnel using the handoffs pattern. The agent grounds it's responses in data stored in a Postgres database with pgvector for semantic search. The database is deployed as an Model Context Protocol (MCP) server, that exposes several tools the agent can use to quickly access data. Since the agent is using the Responses API, it can easily connect to MCP servers and comes with several build in tools like a code interpreter and image genration. Get started now.

What you'll learn

• How to use LangChain's Handoff pattern for multistep tasks.
• How to use Middleware in LangChain to refine the users query, manage context and validate response groundedness. (gpt-5.4-mini will power the main agent and middleware tasks will use gpt-5-nano)
• How to back retrieval with Postgres + pgvector: HNSW indexes over text-embedding-3-small vectors for case studies, KB articles, and the product catalogue.
• How to expose CRM-style tools as MCP tools with FastMCP: search_case_studies, search_kb_articles, get_pricing, compare_plans — over streamable HTTP.
• How to use Entra ID (Managed Identity) for keyless auth to Azure OpenAI and Postgres.

Architecture

The core LangChain Agent and the PostgreSQL MCP server are deployed independently as two Container Apps:

The agent is the only public-facing service. The MCP server is reachable only from inside the Container Apps environment. All Azure access uses a user-assigned managed identity with RBAC to Azure OpenAI and PostgreSQL.

The 6-step sales funnel

Each step is a small system prompt plus a filtered tool subset. The agent moves between steps by calling state-mutating tools (set_intent, advance_to_step, back_to_greet, escalate_to_ae):

The state machine lives in agent/app/middleware/steps.py; the per-step prompts are plain text in agent/app/prompts/.

Prerequisites

• An Azure subscription. Create one for free.
• Azure Developer CLI (azd).
• Azure CLI.
• Python 3.11+ (only required for local development).
• Docker (only required for the full local stack).

The fastest path is to open the repo in GitHub Codespaces — every tool above is preinstalled.

Quick start

Deploy the app to Azure:

az login
azd auth login
azd up

azd up provisions Azure OpenAI (wit

... View full README on GitHub