{"id":16299,"date":"2025-04-24T07:54:38","date_gmt":"2025-04-24T15:54:38","guid":{"rendered":"https:\/\/live-cometml.pantheonsite.io\/?p=13435"},"modified":"2025-06-05T11:49:44","modified_gmt":"2025-06-05T11:49:44","slug":"comet-product-releases-april2025-2","status":"publish","type":"post","link":"https:\/\/www.comet.com\/site\/blog\/comet-product-releases-april2025-2\/","title":{"rendered":"Major Releases: MCP Server & Google Agent Dev Kit Support"},"content":{"rendered":"\n

We\u2019ve just rolled out two major updates in Opik, Comet\u2019s open-source LLM evaluation<\/a> platform, that make it easier than ever to build, test, and evaluate your AI agents \u2014 all in one place!<\/p>\n\n\n\n

Opik\u2019s Model Context Protocol (MCP)<\/a> Server, which simplifies how you manage prompts, traces, and projects across your LLM stack, is now live! We\u2019ve expanded support for agentic development with a new integration for Google\u2019s Agent Development Kit (ADK)<\/a>, providing teams building with Gemini models and Google AI tools with full trace visibility directly in Opik.<\/p>\n\n\n\n

Read on for more details on these releases and how to start using them \u2014 plus, check out a powerful new integration with OpenAI\u2019s Agents SDK<\/a>, a behind-the-scenes look at our engineering team\u2019s architectural decisions building Opik<\/a>, and a roundup of community events where you can connect with fellow AI developers and stay on top of the latest trends.<\/p>\n\n\n\n

Opik: Model Context Protocol Server<\/h2>\n\n\n\n
\"Opik<\/figure>\n\n\n\n

<\/p>\n\n\n\n

Opik’s MCP Server<\/a> is an open-source implementation of the Model Context Protocol that provides a unified interface for accessing Opik\u2019s capabilities. It supports multiple transport mechanisms (like stdio and SSE) for flexible integration into IDEs like Cursor and other environments. With MCP, you can manage prompts, projects, and traces through a consistent API, streamlining everything from local development to production monitoring.<\/p>\n\n\n\n

View Documentation \u2192<\/a><\/p>\n\n\n\n

Opik: Agent Development Kit (ADK) Support<\/h2>\n\n\n\n

Opik now integrates directly with Google\u2019s Agent Development Kit (ADK)<\/a>, a framework for building AI agents using Gemini models and Google AI tools. ADK supports popular LLMs and open-source components, making it easy to start with simple agents or scale to complex, multi-agent systems. With this integration, Opik captures trace data for all ADK agent executions, giving you deep visibility into agent behavior and orchestration.<\/p>\n\n\n\n

View Documentation \u2192<\/a><\/p>\n\n\n\n

Opik: OpenAI Agents SDK Integration<\/h2>\n\n\n\n

Opik now supports a native integration with OpenAI\u2019s new Agents framework \u2014 a powerful set of building blocks for creating agentic systems. Agents include support for all OpenAI models, tool use via function calling, built-in memory and knowledge via vector stores and embeddings (OpenAI & Anthropic), and parallel Guardrail checks for secure and efficient execution. With just one line of code, you can connect Agents to Opik and analyze and debug the full execution flow.<\/p>\n\n\n\n

View Documentation \u2192<\/a><\/p>\n\n\n\n

Insights From the Comet Engineering Team<\/h2>\n\n\n\n
\"building<\/figure>\n\n\n\n

When we started building Opik, we knew it needed to be both open source and massively scalable, with extensibility to perform a wide variety of tasks well for teams integrating LLMs into their own applications. In this behind-the-scenes look, the project\u2019s engineering lead shares insight into the architectural decisions and technical details we chose to meet those requirements. We hope it\u2019s useful for others building complex production systems.<\/p>\n\n\n\n

Read Here \u2192<\/a><\/p>\n\n\n\n

\"SelfCheckGPT-LLM-Blog\"<\/figure>\n\n\n\n

<\/p>\n\n\n\n

Explore how SelfCheckGPT offers a reference-free approach to detecting hallucinations in LLM outputs. You will learn how response consistency can be utilized for evaluation, its optimal application, and how it can be integrated into broader evaluation pipelines.<\/p>\n\n\n\n

Read Here \u2192<\/a><\/p>\n\n\n\n

Connect & Learn with Fellow GenAI Developers<\/h2>\n\n\n\n

Join us live in the coming weeks for the following demos, workshops, prizes, and opportunities to connect with fellow AI builders:<\/p>\n\n\n\n