AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
MCP verified MIT Self-run

Building With The Claude API

mcp-hyegojarllys-building-with-the-claude-api · by HyegoJarllys

Hands-on portfolio from Anthropic's official Claude API course — agents, tool use, RAG, evaluations, MCP, prompt engineering.

↗ Repository
— No reviews yet
0 installs
3 views
0.0% view→install

Install

$ agentstack add mcp-hyegojarllys-building-with-the-claude-api

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Building With The Claude API? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Building with the Claude API — Hands-on Portfolio

A hands-on study portfolio focused on LLM Engineering, building agents, RAG pipelines, Evaluation and consuming language model APIs with the Anthropic Claude API.

About this repository

This repository documents my hands-on journey through Anthropic's "Building with the Claude API" course, covering everything from API access fundamentals to advanced agent and workflow architectures.

Each module contains notebooks, scripts, and functional projects that demonstrate real-world implementations—not just theory.

Main Stack: Python · Claude API · RAG · Tool Use · MCP · Embeddings · Prompt Engineering

Module One

  • Acessing the claude code API for response the text question and making the request
  • implement mult-turn conversation, whith function that append response the assistem and user prompt to the final prompt ( search for more ways to the implement this feature)
  • configure prompt system using prompt engineering for more realiability in the final output
  • configure temperature and add to the main function for distinc more asrerw deterministic or criative
  • response streaming for more expresive user experiense and optimize the user adoption
  • control model output using the stop sequence, this very utility for nlp and filter the content structured data as such JSON in Liz ouvidoria - ( pessoal project)

Module Two

  • Prompt engineering optimization.
  • tipical evaluation pipeline whit : create dataset, create judge agent whith prompt optimized for the evaluation or function whit api call ( grading model).
  • run the pipeline, evaluation the asrwer and repeat whith optimization in the main prompt

Module Two

  • Implement recent improvements for prompt engineering such :
  • beeing clear and direct - ( use adjective in imperative mode )
  • XLM tags, for more clarity and concision in the prompt
  • Few-shot exemples(provide examples), for instruct llm to response the output whith caracteristics previsibility.

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in AI & ML