https://flatt.tech/research/tags/mcp/ Recent content in MCP on GMO Flatt Security Research Hugo en Wed, 29 Oct 2025 00:00:00 +0000 https://flatt.tech/research/posts/securing-llm-function-calling/ Wed, 29 Oct 2025 00:00:00 +0000 https://flatt.tech/research/posts/securing-llm-function-calling/ <h2 id="introduction">Introduction</h2> <p>Hello. I’m Yamakawa (<a href="https://x.com/dai_shopper3" target="_blank" rel="noopener">@dai_shopper3</a> ), a security engineer at GMO Flatt Security, Inc.</p> <p>LLMs exhibit high capabilities in various applications such as text generation, summarization, and question answering, but they have several limitations when used alone. Fundamentally, a standalone model only has the function of generating strings in response to input natural language. Therefore, to create an autonomous AI based on an LLM, a means to exchange information with the outside and execute concrete actions is necessary.</p>