22.4 C
New York
Sunday, July 27, 2025

Introducing Assist for AI Brokers and Mannequin Context Protocol (MCP)


This weblog publish focuses on new options and enhancements. For a complete checklist, together with bug fixes, please see the launch notes.

We’re rolling out two key options that change the way you construct AI utilizing Clarifai: help for AI brokers and the Mannequin Context Protocol (MCP).

AI Brokers: Constructing Smarter, Autonomous AI

AI brokers are a giant step past single-task AI fashions. As a substitute of simply doing one factor, an agent can purpose, plan, and take a number of actions to realize a bigger purpose. Consider them as AI packages that may break down advanced issues and use completely different instruments or fashions to get the job accomplished.

With this launch, we’re making it simpler to construct these brokers on Clarifai. This implies you’ll be able to:

  • Create goal-oriented AI: Design methods that work in the direction of particular goals, not simply offering remoted solutions.
  • Chain collectively AI capabilities: Mix a number of fashions and instruments on our platform (or exterior ones) in sequence to resolve extra advanced issues.
  • Automate multi-step processes: Scale back handbook effort by having AI deal with whole workflows.

This opens up potentialities for extra superior AI functions that may make choices and adapt to conditions. 

To point out you what and how one can construct AI Brokers, we have created an AI Weblog Writing Agent utilizing Clarifai and CrewAI! 

On this video, we construct an AI-powered weblog writing agent that generates full weblog posts from scratch. We use:

  • CrewAI to handle agent orchestration
  • Gemini 2.5 Professional mannequin powered by Clarifai
  • Streamlit to create a easy and interactive UI

MCP: Giving AI Brokers Actual-World Context

For AI brokers to be really helpful, they want entry to real-time data from outdoors their inner knowledge. The Mannequin Context Protocol (MCP) solves this by offering a standardized means for AI fashions and brokers to work together with exterior knowledge sources and APIs.

We have built-in MCP, permitting you to:

  • Join brokers to your knowledge: Bridge your AI brokers together with your firm’s databases, knowledge lakes, and different inner methods.
  • Entry stay knowledge: Give your brokers present data from exterior APIs, like monetary knowledge, information, or sensor readings.
  • Construct customized knowledge bridges: Create your personal MCP servers to tailor how your AI brokers entry and use exterior context.

Combining AI brokers with MCP means your AI cannot solely suppose and plan but additionally actively fetch and use real-world data, making your AI functions extra highly effective and related. Study extra right here.

Clarifai now gives an OpenAI-compatible API endpoint, permitting you to make use of your present OpenAI code and workflows to run inferences with Clarifai fashions, together with those who combine or wrap OpenAI fashions.

The compatibility layer mechanically interprets OpenAI-style requests into Clarifai API calls, so you’ll be able to entry Clarifai’s broad mannequin library as customized instruments inside your OpenAI-based initiatives.

This removes the necessity to rewrite your code for Clarifai’s native API, making integration quick and easy for groups already accustomed to OpenAI.

Beneath is an instance that makes use of the OpenAI Python consumer library to work together with a Clarifai mannequin by way of Clarifai’s OpenAI-compatible API endpoint. Learn extra right here

Now we have made quite a few enhancements to the Python SDK to reinforce stability, usability, and integration capabilities:

We’re excited in regards to the new Agentic and MCP help in Clarifai and are trying ahead to seeing the sorts of functions the neighborhood builds round it. Take a look at our video tutorial on constructing an AI Weblog Writing Agent to see AI Brokers in motion. You can too discover extra examples right here.

Discover the documentation and begin constructing as we speak. We’ll even be including extra agent examples and templates quickly, so keep tuned.

In case you have any questions, ship us a message on our Neighborhood Discord channel. Thanks for studying!



Related Articles

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Latest Articles