Specify MCP Servers in LLM Calls
...takes just 3-5 lines of code.
Codegen: Idea to feature in seconds!
Codegen lets you describe any code modification and let AI do the work.
We’ve integrated it into Slack, and now we can review PRs, ship features, and start new projects, all without ever leaving a chat window.
Below, I asked it to produce a video RAG using the Gemini API:
Codegen returned with a PR, which resulted in this:
Explore Codegen yourself here →
And yes, you can use it for free, just connect your GitHub account and assign a job to Codegen Agents.
Thanks to Codegen for partnering today!
Specify MCP Servers in LLM Calls
OpenAI recently added support for remote MCP servers in the Responses API.
This way, you can connect models to tools available on any MCP server in just a few lines of code.
In the code below, we integrated the MindsDB MCP server:
This single MCP server lets you query 200+ data sources like: databases, warehouses, SaaS apps, social platforms, etc., all in plain English or SQL.
We asked about the available MCP tools, and it responded as expected!
Steps:
Initiate your OpenAI client.
In the response API, specify your MCP server as the tools parameter.
Specify your query in the input parameter.
Done!
This integration makes it super easy to use MCP tools beyond popular products like Claude and Cursor.
You can read about this update in the OpenAI docs here →
Thanks for reading!
P.S. For those wanting to develop “Industry ML” expertise:
At the end of the day, all businesses care about impact. That’s it!
Can you reduce costs?
Drive revenue?
Can you scale ML models?
Predict trends before they happen?
We have discussed several other topics (with implementations) that align with such topics.
Here are some of them:
Learn how to build Agentic systems in a crash course with 14 parts.
Learn how to build real-world RAG apps and evaluate and scale them in this crash course.
Learn sophisticated graph architectures and how to train them on graph data.
So many real-world NLP systems rely on pairwise context scoring. Learn scalable approaches here.
Learn how to run large models on small devices using Quantization techniques.
Learn how to generate prediction intervals or sets with strong statistical guarantees for increasing trust using Conformal Predictions.
Learn how to identify causal relationships and answer business questions using causal inference in this crash course.
Learn how to scale and implement ML model training in this practical guide.
Learn techniques to reliably test new models in production.
Learn how to build privacy-first ML systems using Federated Learning.
Learn 6 techniques with implementation to compress ML models.
All these resources will help you cultivate key skills that businesses and companies care about the most.