Welcome to Israel's first conference dedicated to Context Protocol (MCP) – an innovative open standard transforming how AI systems communicate with data sources.
During the conference, we will explore how the MCP protocol enables universal connections between advanced models and content repositories, business tools, and development environments. We'll learn how fragmented integrations can be replaced with a unified protocol, helping AI systems generate better and more relevant responses.
Leading industry experts will present practical MCP applications and provide insights on ways organizations can leverage this innovative technology to connect their internal systems with AI tools.
Join us in building the future of context-aware artificial intelligence!
30.06.2025
09:00-14:00
Virtual
Tickets are free for the first 100 registrants.
09:00-9:05
Opening Remarks
Uri Eliabayev
Founder at MDLI
9:05-9:35
Lego for LLMs: Snapping Together Agentic Workflows with MCP
Hans Ramsl
AI Solutions Engineer at Weights & Biases
9:35-9:55
TBD
9:55- 10:15
TBD
10:15-10:35
Build Your Own MCP - Practical Lessons From Building Hud's MCP for Production Runtime Context
May Walter
Co-Founder & CTO at Hud
10:35-10:50
Break
10:50- 11:10
Letting Data Talk: Multi-Agent Orchestration with MCP
We built a conversational analytics system where a central LLM interfaces with the user and uses MCP to orchestrate a network of specialized, tool-augmented agents. The goal: make organizational data accessible to anyone through natural language — no SQL, schema knowledge, or dashboards required.
The central LLM routes tasks to agents dedicated to specific roles: querying databases, running deep data investigations, visualizing results, and — crucially — learning over time. Our Memory Agent observes all interactions and query runs, stores insights, and improves future performance by adapting responses and optimizing tool usage. Together, these agents operate as an intelligent, modular system controlled via MCP.
In this talk, we’ll share the architecture, development workflow, and practical tips for building and deploying multi-agent systems with MCP. We’ll cover lessons from experimentation, how to design reusable agents, and how to enable memory and learning across agent runs.
Miriam Horovicz
Senior AI Engineer at Fiverr
Gal Benbeniste
Senior AI Engineer at Fiverr
11:10-11:30
Cutting Edge MCPs - GitMCP and mcp-ui
Liad Yosef
Senior Staff Developer at Shopify
Ido Salomon
Cloud Architect at Palo Alto
11:30-11:50
WorkbenchMCP - stable, agentic development at scale
Present our sterile environment(s) for AI agents to create components at scale, then integrate them with our agentic IDE.
Ori Nachum
AI Expert, Innovation team at Tipalti
11:50-12:10
Applying MCPs + agents for large codebase enterprise use cases
Bar Fingerman
AI Eng Manager at Qodo
12:40-13:00
One MCP to rule them all: securing MCPs
Or Oxenberg
Senior Ml engineer at Lasso security
13:00-13:20
AI first - to road we pursue to use mcp to make monday ai driven
In this lecture, I'll explain the road we took from basic MCP to hosted MCP. How do we make it work with different clients like Claud, Copilot, Cursor… I also deep dive into how we overcome the limit tool and the dynamic tool usages we made (we are using graphql for api calls).
Rom Kadria
Software engineer at monday.com