{"id":"azure-samples-mcp-agent-langchainjs","name":"mcp-agent-langchainjs","af_score":48.5,"security_score":48.2,"reliability_score":28.8,"what_it_does":"A TypeScript/Node.js sample application that demonstrates building an AI agent using LangChain.js with Model Context Protocol (MCP) tools to browse a burger menu, place orders, and query order status. It includes a burger ordering REST-style backend, an MCP server exposing burger operations as MCP tools (serverless/HTTP), and agent UIs/APIs/CLI for interacting with the toolset.","best_when":"Used as a learning/reference implementation or starter template for integrating MCP tools into an LLM agent workflow (especially in Azure serverless contexts).","avoid_when":"Avoid using it as-is for sensitive production workloads (auth/authorization, auditing, and operational hardening details are not fully evidenced in the provided README).","last_evaluated":"2026-03-30T13:39:28.536834+00:00","has_mcp":true,"has_api":true,"auth_methods":["User authentication with sessions history (exact mechanism not specified in provided README excerpt)","Azure auth/CLI for deployment (azd auth login)"],"has_free_tier":true,"known_gotchas":["Tool semantics like delete_order_by_id likely depend on order status (e.g., pending) and may fail if state has changed; no guidance is provided in the excerpt.","Local runs use in-memory storage, so order/history behavior differs from deployed Cosmos DB-backed persistence."],"error_quality":0.0}