--- title: "Roman Gelembjuk (@gelembjuk) | Hashnode" description: "Building AGI. Read the latest articles by Roman Gelembjuk on Hashnode." url: "https://hashnode.com/@gelembjuk" --- @gelembjuk # Roman Gelembjuk @gelembjuk · Joined March 2025 Building AGI ### [Implementing the Most Universal MCP Server Ever](https://gelembjuk.hashnode.dev/implementing-the-most-universal-mcp-server-ever?utm_source=hashnode&utm_medium=feed) It seems the MCP hype is starting to slow down a bit. After 6–8 months of high enthusiasm, the community is beginning to realize that MCP is not a magic bullet. In some MCP listings, you’ll find more than 10,000 servers doing all sorts of things. Nat... 6 min read · [gelembjuk.hashnode.dev](https://gelembjuk.hashnode.dev/implementing-the-most-universal-mcp-server-ever?utm_source=hashnode&utm_medium=feed) [May 23, 2025](https://hashnode.com/posts/implementing-the-most-universal-mcp-server-ever/68309c53c0f008b63a21af61) ### [Building More Independent AI Agents: Let Them Plan for Themselves](https://gelembjuk.hashnode.dev/building-more-independent-ai-agents-let-them-plan-for-themselves?utm_source=hashnode&utm_medium=feed) I continue to explore one of my favorite topics: how to make AI agents more independent. This blog is my way of organizing ideas and gradually shaping a clear vision of what this might look like in practice. The Dream That Started It All When large l... 8 min read · [gelembjuk.hashnode.dev](https://gelembjuk.hashnode.dev/building-more-independent-ai-agents-let-them-plan-for-themselves?utm_source=hashnode&utm_medium=feed) [May 16, 2025](https://hashnode.com/posts/building-more-independent-ai-agents-let-them-plan-for-themselves/68275bfbcd3b5b829e057477) ### [Inside the LLM Black Box: What Goes Into Context and Why It Matters](https://gelembjuk.hashnode.dev/inside-the-llm-black-box-what-goes-into-context-and-why-it-matters?utm_source=hashnode&utm_medium=feed) Large Language Models (LLMs) like GPT-4, Claude, and Mistral appear to produce intelligent responses — but the magic lies in how they consume and interpret context. Understanding what goes into an LLM's context and how it shapes output is critical fo... 9 min read · [gelembjuk.hashnode.dev](https://gelembjuk.hashnode.dev/inside-the-llm-black-box-what-goes-into-context-and-why-it-matters?utm_source=hashnode&utm_medium=feed) [May 12, 2025](https://hashnode.com/posts/inside-the-llm-black-box-what-goes-into-context-and-why-it-matters/68227113ac3ebe110e3c9876) ### [Easily Switch Transport Protocols in MCP Servers](https://gelembjuk.hashnode.dev/easily-switch-transport-protocols-in-mcp-servers?utm_source=hashnode&utm_medium=feed) I would like to expose one more benefit of the Model Context Protocol (MCP) — the ability to easily change the transport protocol. There are three different transport protocols available now, and each has its own benefits and drawbacks. However, if a... 8 min read · [gelembjuk.hashnode.dev](https://gelembjuk.hashnode.dev/easily-switch-transport-protocols-in-mcp-servers?utm_source=hashnode&utm_medium=feed) [May 7, 2025](https://hashnode.com/posts/easily-switch-transport-protocols-in-mcp-servers/681bd2d4b422248d1957ef9b) ### [An Underrated Feature of MCP Servers: Client Notifications](https://gelembjuk.hashnode.dev/an-underrated-feature-of-mcp-servers-client-notifications?utm_source=hashnode&utm_medium=feed) In recent months, the Model Context Protocol (MCP) has gained a lot of traction as a powerful foundation for building AI assistants. While many developers are familiar with its core request-response flow, there's one feature that I believe remains un... 5 min read · [gelembjuk.hashnode.dev](https://gelembjuk.hashnode.dev/an-underrated-feature-of-mcp-servers-client-notifications?utm_source=hashnode&utm_medium=feed) [May 6, 2025](https://hashnode.com/posts/an-underrated-feature-of-mcp-servers-client-notifications/681a348312681401e5c608dc)