VibeGuard MCP
Enables policy-style auditing of content through the audit_vibe MCP tool to enforce configurable guardrails. Supports both local stdio and serverless Streamable HTTP deployment via Vercel for flexible integration with MCP clients.
README
Master AI Agentic Engineering - build autonomous AI Agents
6 week journey to code and deploy AI Agents with OpenAI Agents SDK, CrewAI, LangGraph, AutoGen and MCP

If you're looking at this in Cursor, please right click on the filename in the Explorer on the left, and select "Open preview", to view the formatted version.
I couldn't be more excited to welcome you! This is the start of your 6 week adventure into the powerful, astonishing and often surreal world of Agentic AI.
Before you begin
I'm here to help you be most successful! Please do reach out if I can help, either in the platform or by emailing me direct (ed@edwarddonner.com). It's always great to connect with people on LinkedIn to build up the community - you'll find me here:
https://www.linkedin.com/in/eddonner/
And this is new to me, but I'm also trying out X/Twitter at @edwarddonner - if you're on X, please show me how it's done 😂
The not-so-dreaded setup instructions
Perhaps famous last words: but I really, truly hope that I've put together an environment that will be not too horrific to set up!
Any problems, please do contact me.
Important notes for CrewAI week (Week 3)
Windows PC users: you will need to have checked the "gotcha #4" at the top of the SETUP-PC instructions -- installing Microsoft Build Tools.
If you don't do this, then CrewAI will fail with an obscure error involving Chroma..
Then, you will need to run this command in a Cursor Terminal in the project root directory in order to run the Crew commands:
uv tool install crewai==0.130.0 --python 3.12
And in case you've used Crew before, it might be worth doing this to make sure you have the latest:
uv tool upgrade crewai==0.130.0 --python 3.12
This command pins Crew to the same version that I use on the course. If you have any problems with Crew, you could try using the latest version instead, by running this command:
uv tool upgrade crewai --python 3.12
At any point, you can see which version of Crew you have installed with this:
uv tool list
Sidenote: a "tool" with uv is a utility that is installed globally by uv. After installing this tool, you can use "crewai" as a command, and it runs the code associated with this tool.
Then please keep in mind for Crew:
- There are two ways that you can work on the CrewAI project in week 3. Either review the code for each project while I build it, and then do
crewai runto see it in action. Or if you prefer to be more hands-on, then create your own Crew project from scratch to mirror mine; for example, createmy_debateto go alongsidedebate, and write the code alongside me. Either approach works! - Windows users: there's a new issue that was recently introduced by one of Crew's libraries. Until this is fixed, you might get a "unicode" error when you try to run
crewai create crew. If that happens, please try running this command in the Terminal first:$env:PYTHONUTF8 = "1" - Gemini users: in addition to a key in your
.envfile forGOOGLE_API_KEY, you will need an identical key forGEMINI_API_KEY
Super useful resources
- The course resources with videos
- Many essential guides in the guides section
- The troubleshooting notebook
- My overall FAQ page with common issues and questions
API costs - please read me!
This course does involve making calls to OpenAI and other frontier models, requiring an API key and a small spend, which we set up in the SETUP instructions. If you'd prefer not to spend on API calls, there are cheaper alternatives like DeepSeek and free alternatives like using Ollama!
Details are here.
Be sure to monitor your API costs to ensure you are totally happy with any spend. For OpenAI, the dashboard is here.
ABOVE ALL ELSE -
Be sure to have fun with the course! You could not have picked a better time to be learning about Agentic AI. I hope you enjoy every single minute! And if you get stuck at any point - contact me.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.