Chandana Vs Punith

devops-infra MCP Server

30-day challenge: AWS (Chandana) + Agentic AI (Punith). Daily notes, working code, and the beginner-to-advanced gotchas tutorials skip — Lambda, IAM, RAG, MCP, Bedrock, LangChain, and more.

Verified
devops-infradevops-infraaws
5 views4 stars0 forks

Why This Matters

Discovered via github-topic:mcp and last synced 4mo ago.

Verified
Source
github-topic:mcp
Stars
4
Last synced
4mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
13
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (13)

Day

Topic

4

MCP (Model Context Protocol) — building servers, hosting on AWS, Claude Desktop integration

3

RAG end-to-end — embeddings, chunking, OpenSearch, Bedrock Knowledge Bases, reranking

6

Containers — ECS, EKS, Fargate, Dockerized agents, MCP servers in containers

11

Cost Optimization — AWS levers (Savings Plans, S3 tiers) + LLM levers (caching, routing)

12

Guardrails & Responsible AI — Bedrock Guardrails, prompt/output filtering, PII, safety eval

7

Bedrock Agents & Knowledge Bases — action groups, ingestion jobs, agent traces

1

AWS Lambda & Python Lambda — handler, event, context, triggers, agent-tool patterns

9

DynamoDB & Agent Memory — single-table design, short/long-term memory patterns

2

IAM & Security — policies, AssumeRole, prompt injection, secrets handling

10

Step Functions & Agent Orchestration — state machines, retries, HITL, LangGraph parallels

5

Observability — CloudWatch, X-Ray, LangSmith, OpenTelemetry, agent traces

8

API Gateway & Agent-Facing APIs — REST/HTTP, streaming, MCP-over-HTTP, OpenAPI for tools