langchain-install-auth
Install and configure LangChain SDK/CLI authentication. Use when setting up a new LangChain integration, configuring API keys, or initializing LangChain in your project. Trigger with phrases like "install langchain", "setup langchain", "langchain auth", "configure langchain API key", "langchain credentials".
Install
mkdir -p .claude/skills/langchain-install-auth && curl -L -o skill.zip "https://mcp.directory/api/skills/download/4701" && unzip -o skill.zip -d .claude/skills/langchain-install-auth && rm skill.zipInstalls to .claude/skills/langchain-install-auth
About this skill
LangChain Install & Auth
Overview
Set up LangChain SDK packages and configure provider authentication. Covers the modular @langchain/* package ecosystem for Node.js/TypeScript and langchain-* packages for Python.
Prerequisites
- Node.js 18+ or Python 3.9+
- Package manager (npm/pnpm or pip/poetry)
- API key from at least one LLM provider (OpenAI, Anthropic, Google)
Instructions
Step 1: Install Core Packages (TypeScript)
set -euo pipefail
# Core + one provider (pick what you need)
npm install @langchain/core @langchain/openai
# Additional providers
npm install @langchain/anthropic # Claude models
npm install @langchain/google-genai # Gemini models
npm install @langchain/community # 100+ community integrations
# Common companions
npm install @langchain/textsplitters # Text chunking for RAG
npm install @langchain/pinecone # Pinecone vector store
npm install zod # Schema validation (structured output)
Step 2: Install Core Packages (Python)
set -euo pipefail
pip install langchain langchain-core
# Provider packages (install only what you need)
pip install langchain-openai # ChatOpenAI, OpenAIEmbeddings
pip install langchain-anthropic # ChatAnthropic
pip install langchain-google-genai # ChatGoogleGenerativeAI
pip install langchain-community # Community integrations
Step 3: Configure Authentication
# Create .env file (add to .gitignore!)
cat > .env << 'ENVEOF'
# OpenAI — https://platform.openai.com/api-keys
OPENAI_API_KEY=sk-...
# Anthropic — https://console.anthropic.com/
ANTHROPIC_API_KEY=sk-ant-...
# Google — https://aistudio.google.com/apikey
GOOGLE_API_KEY=AI...
# LangSmith (optional but recommended) — https://smith.langchain.com
LANGSMITH_TRACING=true
LANGSMITH_API_KEY=lsv2_...
LANGSMITH_PROJECT=my-project
ENVEOF
echo '.env' >> .gitignore
Step 4: Verify Connection (TypeScript)
import { ChatOpenAI } from "@langchain/openai";
import { ChatAnthropic } from "@langchain/anthropic";
import "dotenv/config";
// OpenAI
const openai = new ChatOpenAI({ model: "gpt-4o-mini", temperature: 0 });
const res1 = await openai.invoke("Say 'OpenAI connected'");
console.log("OpenAI:", res1.content);
// Anthropic
const anthropic = new ChatAnthropic({ model: "claude-sonnet-4-20250514" });
const res2 = await anthropic.invoke("Say 'Anthropic connected'");
console.log("Anthropic:", res2.content);
Step 5: Verify Connection (Python)
import os
from dotenv import load_dotenv
load_dotenv()
from langchain_openai import ChatOpenAI
from langchain_anthropic import ChatAnthropic
# OpenAI
llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
print(llm.invoke("Say 'connected'").content)
# Anthropic
llm2 = ChatAnthropic(model="claude-sonnet-4-20250514")
print(llm2.invoke("Say 'connected'").content)
Package Architecture
@langchain/core # Base abstractions: Runnables, prompts, output parsers
├── @langchain/openai # ChatOpenAI, OpenAIEmbeddings
├── @langchain/anthropic # ChatAnthropic
├── @langchain/google-genai # ChatGoogleGenerativeAI
├── @langchain/community # 100+ integrations
├── @langchain/pinecone # PineconeStore
├── @langchain/textsplitters # RecursiveCharacterTextSplitter
└── langchain # High-level: agents, chains, tools
Every @langchain/* package depends on @langchain/core. You never import from langchain directly for base types -- always use @langchain/core for prompts, output parsers, messages, and runnables.
Error Handling
| Error | Cause | Fix |
|---|---|---|
Cannot find module '@langchain/openai' | Package not installed | npm install @langchain/openai |
AuthenticationError: Incorrect API key | Invalid or missing key | Check .env and dotenv/config import |
Could not import @langchain/core | Version mismatch | Ensure all @langchain/* packages share same minor version |
RateLimitError | Quota exceeded | Check provider dashboard, implement backoff |
ENOTFOUND api.openai.com | Network blocked | Check firewall/proxy settings |
Troubleshooting Version Conflicts
# Check installed versions (all should share same minor)
npm ls @langchain/core
# Fix version conflicts
npm install @langchain/core@latest @langchain/openai@latest @langchain/anthropic@latest
Resources
Next Steps
After successful auth, proceed to langchain-hello-world for your first chain.
More by jeremylongshore
View all skills by jeremylongshore →You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
fastapi-templates
wshobson
Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.
Related MCP Servers
Browse all serversMCP Installer simplifies dynamic installation and configuration of additional MCP servers. Get started easily with MCP I
Pica is automated workflow software for business process automation, integrating actions across services via a unified i
Manage and secure Hellō authentication apps with Hellō Admin — create, configure, and monitor user authentication quickl
Fetch Jampp Reporting campaign metrics (spend, impressions, clicks, installs) across date ranges with automated authenti
install.md — Step-by-step MCP server guides to install and configure coding agents and use your software fast.
MCP Toolbox for Databases by Google. An open-source server that lets AI agents query Cloud SQL, Spanner, AlloyDB, and ot
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.