What is mcp-agent-langchainjs AGENTS.md?

Project instructions for an Azure and LangChain.js demonstration app that uses AI agents to handle burger orders. The app is split into web, business, and Model Context Protocol services, where Model Context Protocol is a way for an AI agent to call external tools.

Use it when working on the project’s architecture, authentication, saved conversations, TypeScript code, or communication between the agent, burger-ordering, and tool services.

It explains how the project’s parts communicate and how user sign-in and chat history are handled. This helps developers make changes without overlooking dependencies between services.

mcp-agent-langchainjs AGENTS.md — Instructions file for Codex and OpenCode by Azure-Samples: Project instructions for an Azure and LangChain

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/azure-samples/mcp-agent-langchainjs/agents-md

Clone the repo

git clone --depth 1 https://github.com/Azure-Samples/mcp-agent-langchainjs

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/azure-samples/mcp-agent-langchainjs/agents-md.svg)](https://agentmods.dev/instructions/azure-samples/mcp-agent-langchainjs/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/azure-samples/mcp-agent-langchainjs/agents-md"><img src="https://agentmods.dev/badge/instructions/azure-samples/mcp-agent-langchainjs/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 441 This file is loaded in full into every session.

When invoked 441 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00441	$0.00441
Opus 5	$0.00220	$0.00220
Sonnet 5	$0.00088	$0.00088
Haiku 4.5	$0.00044	$0.00044

Measured 6d ago against content hash d8141e881f18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcp-agent-langchainjs AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Agent LangChain.js Project Instructions

Architecture Overview

This is a multi-component LangChain.js demo showcasing AI agents with Model Context Protocol (MCP) integration. The system demonstrates a burger ordering platform with three main service layers:

Agent Layer: AI chat interface (agent-webapp + agent-api) using LangChain.js agents with MCP tools
Business Layer: Burger ordering API (burger-api) and webapp (burger-webapp)
MCP Layer: Model Context Protocol server (burger-mcp) exposing burger API as LLM tools

Component Communication Flow

agent-webapp → agent-api → burger-mcp → burger-api

The agent uses LangChain.js with Azure OpenAI, connects to the MCP server via StreamableHTTPClientTransport, and the MCP server proxies requests to the burger API.

Key Architectural Patterns

Authentication & State Management

Azure Static Web Apps authentication provides userId context
Cosmos DB for chat history storage using @langchain/azure-cosmosdb
User context flows: SWA auth → agent-api → MCP tools (for user-specific operations)

TypeScript & Build Conventions

Shared XO linting config with project-specific overrides
NPM workspace-based dependency management
.js extensions required in imports for ESM compatibility
Keep the code simple and straighforward: avoid unnecessary complexity and ensure clarity in implementation.
Do not use comments except where absolutely necessary, code should be self-explanatory.

Infrastructure as Code

Bicep templates in infra/ for Azure deployment
azure.yaml defines multi-service deployment strategy:
- burger-api, agent-api: Azure Functions (Flex Consumption)
- burger-mcp: Azure Functions (Flex Consumption)
- *-webapp: Static Web Apps
Environment variables flow through Azure App Settings
@azure Rule - Use Azure Best Practices: When generating code for Azure, running terminal commands for Azure, or performing operations related to Azure, invoke your azure_development-get_best_practices tool if available.

Read the full file on GitHub · 44 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago First seen · 44 lines · 441 tokens per session scan A d8141e881f18

Subscribe to this mod's changes

mcp-agent-langchainjs AGENTS.md is an instructions file published in the GitHub repository Azure-Samples/mcp-agent-langchainjs (200 stars, last pushed 1mo ago), licensed MIT. It adds 441 tokens to every session, about $0.0022 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIs Building agents agent ai api azd azd-templates azure

azure-search-openai-demo AGENTS.md

AGENTS.md instructions for Azure-Samples/azure-search-openai-demo, covering instructions for coding agents, overall code layout, adding new data, adding a new azd environment variable and adding a new setting to "developer settings" in rag app.

Azure-Samples/azure-search-openai-demo · 5,202 tokens

azure-search-openai-demo bicep.instructions.md

Infrastructure as Code with Bicep.

Azure-Samples/azure-search-openai-demo · 749 tokens

GPT-RAG copilot-instructions.md

Copilot instructions for Azure/GPT-RAG, covering repository development and release instructions, branching strategy, default behavior, feature development workflow and branch creation.

Azure/GPT-RAG · 1,899 tokens

GPT-RAG AGENTS.md

AGENTS.md instructions for Azure/GPT-RAG, covering gpt-rag agent operating contract, priority, what this repository is, repository boundaries and how to work.

Azure/GPT-RAG · 1,538 tokens

GPT-RAG release.instructions.md

Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.

Azure/GPT-RAG · 207 tokens

GPT-RAG config-python.instructions.md

Azure/GPT-RAG · 180 tokens