WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe - Virtual Stage • Jul 2, 2026 • Session details

Plan to link your LLM to your production database? What could possibly go wrong?

Calvin Seward

What stops a prompt injection from tricking your LLM into dropping production tables? Learn to safely proxy database interactions using a secure Model Context Protocol server.

Pause
Mute Enter Fullscreen
#1 about 5 min

Standardizing modern database interactions through user interfaces

Traditional search filters create frustrating user experiences when querying complex databases.

#2 about 2 min

Revolutionizing database search queries with language models

Integrating relational data with artificial intelligence enables intuitive and precise natural language searches.

#3 about 4 min

Enabling direct language model interaction with database structures

Defining JSON schemas as tools allows models to autonomously formulate and execute database read queries.

#4 about 8 min

Exposing critical vulnerabilities in direct language model database access

Allowing unregulated artificial intelligence querying creates massive security risks including prompt injection and unchecked table deletion.

#5 about 5 min

Implementing model context protocol for secure database communication

Whitelisting specific queries inside a model context protocol server eliminates arbitrary execution and safely enables write access.

#6 about 3 min

Executing verified database write operations with dynamic queries

Coordinating specific parameter extraction through verified tools securely handles complex database inserts.

#7 about 5 min

Optimizing server architecture for scalable large language model operations

Implementing query caching, targeted tool clusters, and pagination reduces token consumption while ensuring reliable data responses.

Matching moments

5:24 min

Contextualizing LLMs with the model context protocol

Alfonso Sandoval Rosas Alfonso Sandoval Rosas · Europe 2026 Virtual

2:18 min

Exploiting exposed language models in commercial applications

Liran Tal Liran Tal · LIVE

1:59 min

Understanding LLMs as vulnerable software services

Alex Soto Alex Soto · WWC 2025

2:25 min

Enhancing AI tool discoverability with Model Context Protocol

Daniel Oh Daniel Oh · WWC Europe 2026

3:26 min

Introducing LLMs as judges for automated testing

Sebastian Messingfeld Sebastian Messingfeld · WWC Europe 2026

5:19 min

Understanding the technical structure of an MCP server

Angie Jones Angie Jones · WWC 2025

More from World Congress 2026 Europe - Virtual Stage

One Does Not Simply Make Architecture Decisions Alone thumbnail
36:15
28 days ago

One Does Not Simply Make Architecture Decisions Alone

Vladas Diržys

From Black Box to Glass Box : Bedrock AgentCore Observability thumbnail
21:15
about 1 month ago

From Black Box to Glass Box : Bedrock AgentCore Observability

Yasemin Aktürk

Leading in Rhythm: How Women Make Better Decisions with Biological Intelligence thumbnail
30:41
about 1 month ago

Leading in Rhythm: How Women Make Better Decisions with Biological Intelligence

Julia Grosse

Better Together: Leveraging Your Observability Tools as a SIEM thumbnail
39:06
about 1 month ago

Better Together: Leveraging Your Observability Tools as a SIEM

Mathias Palmersheim

ChatGPT Apps: From Chat to Checkout thumbnail
30:29
about 1 month ago

ChatGPT Apps: From Chat to Checkout

Aaron Koivunen

Interior Decorating (TypeScript Decorators) thumbnail
29:22
about 1 month ago

Interior Decorating (TypeScript Decorators)

Michael Dowden

Upcoming sessions on this topic

Open session

World Congress 2026 North America

Understanding LLM Architectures: Inside the Design of Modern Models

Jofia Jose Prakash

Enterprise AI Architect at American Chemical Society

Jofia Jose Prakash
Open session

World Congress 2026 North America

Red Teaming Your LLM App -- A Hands-On Threat Model You Can Reuse

Saloni Garg

Senior ML Engineer at Adobe

Saloni Garg
Open session

World Congress 2026 North America

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong
Open session

World Congress 2026 North America

Context Engineering Kung Fu

Carl Lapierre

Tech Lead and AI Engineer at Osedea

Carl Lapierre
Open session

World Congress 2026 North America

Fast, Cheap, and Accurate: Optimizing LLM Inference with vLLM and Quantization

Cedric Clyburn, Legare Kerrison

Cedric Clyburn
Legare Kerrison
Open session

World Congress 2026 North America

Rattlesnakes, LLMs, and the Truly Good Product

Ben Makuh

Senior Staff Engineer @ Miro

Ben Makuh

Related videos

Three years of putting LLMs into Software - Lessons learned thumbnail
26:30
WWC 2025 • 12 months ago

Three years of putting LLMs into Software - Lessons learned

Simon A.T. Jiménez

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails thumbnail
29:00
WWC 2025 • 12 months ago

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails

Alex Soto

Prompt Injection, Poisoning & More: The Dark Side of LLMs thumbnail
23:24
WWC 2025 • 12 months ago

Prompt Injection, Poisoning & More: The Dark Side of LLMs

Keno Dreßel

You are not my model anymore - understanding LLM model behavior thumbnail
24:11
WWC 2025 • 12 months ago

You are not my model anymore - understanding LLM model behavior

Andreas Erben

Using LLMs in your Product thumbnail
31:12
WWC 2024 • almost 2 years ago

Using LLMs in your Product

Daniel Töws

ChatGPT, ignore the above instructions! Prompt injection attacks and how to avoid them. thumbnail
27:32
WWC 2023 • almost 3 years ago

ChatGPT, ignore the above instructions! Prompt injection attacks and how to avoid them.

Sebastian Schrittwieser

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.