In 2 live sessions you'll go from zero to production MCP — configure servers in Claude Code and Cursor, wire up Claude.ai connectors, and build a live integration with your own tools and data.
Instructor: Yash ThakkerSecure payment via Stripe
Oct 31 – Nov 1, 2026
Next cohort
2 live sessions
2 hrs each
Recordings included
1-year access
Intermediate level
Recommended experience
View full agenda
2 days · 2 hours each · All sessions recorded
Understand the MCP host/client/server model — tools, resources, and prompts. Configure MCP in Claude Code and Cursor, connect to real servers (GitHub, Postgres, browser), and understand the difference between local and remote MCP. Also covers Claude.ai connectors so you can wire up integrations without a CLI.
Session 1: MCP Architecture — Hosts, Clients, Servers & Transports
Learn what MCP actually is: a standard protocol that lets AI hosts (Claude Code, Cursor, Claude.ai) talk to MCP servers that expose tools, resources, and prompts. Understand the difference between stdio (local process) and SSE/HTTP (remote) transports. Browse the MCP server ecosystem — Anthropic's official servers, community servers, and the explainx.ai MCP directory.
Session 2: Configure MCP in Claude Code, Cursor & Claude.ai Connectors
Configure MCP servers in Claude Code (.claude/settings.json) and Cursor (mcp_servers config). Connect to GitHub, Postgres, or a browser automation server and make your first live tool call. Then switch to Claude.ai — set up built-in connectors (Google Drive, GitHub, Jira, etc.) for users who don't run a local CLI. Understand when to use each approach.
Go deeper — build a minimal custom MCP server to expose your own data or APIs, apply security best practices, and set up a reproducible team MCP configuration with verified server lists and governance docs.
Session 3: Build a Custom MCP Server
Use the MCP TypeScript or Python SDK to build a simple MCP server that exposes a tool, a resource, or a prompt. This could wrap an internal API, a CSV, a database query, or a custom automation. Test it locally with Claude Code. No prior MCP experience required — we start from the official SDK quickstart and extend it live.
Session 4: MCP Security, Verification & Team Setup
Cover supply-chain risks for MCP servers — typosquatting, prompt injection via tool results, and unverified servers. Learn SkillSpector-style verification patterns and how to review a server's code before running it. Set up a team MCP config with a curated server list, version pinning, and an onboarding doc so every developer on your team starts with the same approved integrations.
Every session has hands-on work. Leave with real deliverables you can use the next morning.
At least 2 MCP servers configured and tested in your Claude Code or Cursor environment, plus Claude.ai connectors for key SaaS tools.
A minimal MCP server you built during the bootcamp — exposing a real tool, resource, or data source from your own stack.
A curated, security-reviewed server list with version pins, a setup guide, and an onboarding checklist for your team.
Real messages from students who trained with Yash across his live AI workshops and bootcamps.
October–November 2026 Run · 2 days · 2 hrs/day · Oct 31 – Nov 1, 2026
$79.00$99.00
20% early bird — ends Oct 24 · Only 50 seats remaining
Included with annual membership — every workshop, $300/yr
faq
Everything you need to know before enrolling.
Comfort with a terminal and basic JSON config files is enough for Sessions 1–2. Sessions 3–4 (building a custom server) work best if you know some TypeScript or Python. The Claude.ai connectors section requires no code at all.
Join 350K+ learners
Live, hands-on, and capped so sessions stay interactive.
Reserve your seat50 seats remaining
Early bird
Founder of AISOLO Technologies; AI entrepreneur & educator
350K+
Students
12+
Yrs exp
3
Startups
Yash Thakker is the founder of AISOLO Technologies and one of the most sought-after AI educators in the country. He's known for one thing above all: by the end of any session, students have already built something — no saving it for 'later.' His classes are built around real-life, happening-right-now examples, zero dry theory, and a teaching energy that makes complex things feel obvious. With over a decade shipping AI products across media, fintech, and edtech, Yash has delivered every learning format imaginable — in-person workshops, live bootcamps, online courses, and hybrid sessions — always exploring new ways to make learning land faster. He's obsessed with what learning looks like for this generation, now that AI changes what's even worth teaching. He has reached 350,000+ learners and is the creator behind Olly.social, BGBlur.com, Infloq.com, and explainx.ai.
