9 MCP Projects for AI Engineers

(explained with visuals & open-source code)

In today’s newsletter:

• ​Trace and evaluate any AI/LLM application.​

• ​Get Agents to browse the web like humans​.

• 9 MCP projects for AI Engineers.

---

Trace and evaluate any AI/LLM application!​

Building an Agent is only the first step.

The real challenge begins when you test it on real-world scenarios, and that too at scale.

​LangWatch lets you add evaluation tracking to any of your existing LLM workflows.

You can keep using pandas and your favorite tools, just add a few lines to start tracking your experiments:

• Initialize an eval (line 3)

• Decorate the LLM workflow logic method (line 5)

• Log the evaluation (line 11)

Done!

You can also integrate LangWatch evaluations into CI/CD workflows so every model update is automatically checked before deployment.

GitHub repo → (don’t forget to star)

---

​Get Agents to browse the web like humans

Stagehand​ allows Agents to independently control a browser.

Integrating its MCP server with Claude Desktop delivers a more reliable alternative to OpenAI Operator.

Here's us testing it live:

Stagehand​ bridges the gap between:

• brittle traditional automation like Playwright, Selenium, etc., and

• unpredictable full-agent solutions like OpenAI Operator.

You can always decide how much control to give to the AI.

100% open-source with 12k+ stars!

---

9 MCP projects for AI Engineers

We have covered several MCP projects in this newsletter before.

Here’s a recap along with visuals & full code walk-through issues:

#1) 100% local MCP client

• An MCP client is a component in an AI app (like Cursor) that establishes connections to external tools. Learn how to build it 100% locally.

• Full walkthrough →

#2) MCP-powered Agentic RAG

• Learn how to create an MCP-powered Agentic RAG that searches a vector database and falls back to web search if needed.

• Full walkthrough →

#3) MCP-powered financial analyst

• Build an MCP-powered AI agent that fetches, analyzes & generates insights on stock market trends, right from Cursor or Claude Desktop.

• Full walkthrough →

#4) MCP-powered Voice Agent

• This project teaches you how to build an MCP-driven voice Agent that queries a database and falls back to web search if needed.

• Full walkthrough →

#5) A unified MCP server

• This project builds an MCP server to query and chat with over 200+ data sources using natural language through a unified interface powered by MindsDB and Cursor IDE.

• Full walkthrough →

#6) MCP-powered shared memory for Claude Desktop and Cursor

• Devs use Claude Desktop and Cursor independently with no context sharing. Learn how to add a common memory layer to cross-operate without losing context.

• Full walkthrough →

#7) MCP-powered RAG over complex docs

• Learn how to use MCP to power an RAG app over complex documents with tables, charts, images, complex layouts, and whatnot.

• Full walkthrough →

#8) MCP-powered synthetic data generator

• Learn how to build an MCP server that can generate any type of synthetic dataset. It uses Cursor as the MCP host and SDV to generate realistic tabular synthetic data.

• Full walkthrough →

#9) MCP-powered deep researcher

• ChatGPT has a deep research feature. It helps you get detailed insights on any topic. Learn how you can build a 100% local alternative to it.

• Full walkthrough →

👉 Over to you: What other MCP projects would you like to learn about?

Thanks for reading!