RAG App on AWSSAFE
Build and deploy a full-stack RAG app on AWS with Terraform, using free tier Gemini Pro, real-time web search using Remote MCP server and Streamlit UI with token based authentication.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
👉 GenAI Roadmap - 2025
End-to-End RAG App with Evaluation on AWS, Integrating Web Search via Remote MCP Server
Terraform-based Infrastructure as Code (IaC) to deploy a complete AWS backend for a Retrieval-Augmented Generation (RAG) application. It integrates with Google’s free-tier Gemini Pro and Embedding models for AI powered document querying and includes a Streamlit UI with token-based authentication for interacting with the app.
👉 Related Remote MCP Server: Web Search using SerpAPI Remote MCP Server based on Streaming Http Transport protocol for Real Time Web Search. It's located within the mcp_servers/ directory of this repository.
👉 Related UI: RAG UI (Streamlit Frontend) A Streamlit-based frontend application designed to interact with the backend infrastructure deployed by this project. It's located within the rag_ui/ directory of this
b1b04b31fefeOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add rag-app-on-aws --env AUTH_ENDPOINT=${AUTH_ENDPOINT} --env DB_SECRET_ARN=${DB_SECRET_ARN} --env GEMINI_SECRET_ARN=${GEMINI_SECRET_ARN} --env MAX_OUTPUT_TOKENS=${MAX_OUTPUT_TOKENS} -- uvx rag-app-on-aws{
"mcpServers": {
"rag-app-on-aws": {
"command": "uvx",
"args": [
"rag-app-on-aws"
],
"env": {
"AUTH_ENDPOINT": "${AUTH_ENDPOINT}",
"DB_SECRET_ARN": "${DB_SECRET_ARN}",
"GEMINI_SECRET_ARN": "${GEMINI_SECRET_ARN}",
"MAX_OUTPUT_TOKENS": "${MAX_OUTPUT_TOKENS}"
}
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
health_check | read | |
web_search | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (15)
.pre-commit-config.yaml
cd src/$DIR && pip install -r requirements.txt -t . || true && zip -r ../../lambda_artifacts/$DIR.zip . && cd ../..
chmod +x ../../scripts/import_resources.sh
# ../../scripts/import_resources.sh "$PROJECT_NAME" "$STAGE" "$AWS_REGION" > /dev/null 2>&1 || true
../../scripts/import_resources.sh "$PROJECT_NAME" "$STAGE" "$AWS_REGION" || true
echo "COGNITO_CLIENT_ID=$COGNITO_CLIENT_ID" > ../../env_vars.env
payload = json.loads(base64.b64decode(token_parts[1] + '==').decode('utf-8'))file_content = base64.b64decode(file_content_base64)
mcp, asyncio, python-dotenv, google-search-results
streamlit, pandas, requests, python-dotenv, PyJWT, plotly
pytest, pytest-cov, moto
boto3, psycopg2-binary
boto3
* Generate an Access Key for either an IAM user with sufficient permissions or the Root user (which has full access) to experiment and create resources defined in Terraform..
images/rag-app.png
Gates applied: no_behavioural_pass.
b1b04b31fefefull audit observations/trust-audit/mcp-server/genieincodebottle__rag-app-on-aws.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | b1b04b31fefe | SAFE | B | 89 | first audit |
Questions
What is the RAG App on AWS MCP server?
Build and deploy a full-stack RAG app on AWS with Terraform, using free tier Gemini Pro, real-time web search using Remote MCP server and Streamlit UI with token based authentication.
What tools does RAG App on AWS expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is RAG App on AWS safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does RAG App on AWS need?
It reads AUTH_ENDPOINT, DB_SECRET_ARN, GEMINI_SECRET_ARN, MAX_OUTPUT_TOKENS and SERPAPI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does RAG App on AWS run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on PyPI as rag-app-on-aws.
How current is this page?
The grade is for one exact copy of the source (b1b04b31fefe), read on 2026-10-07. The repository is watched and re-audited when it changes.