AI RESEARCH
Semantic Tool Discovery for Large Language Models: A Vector-Based Approach to MCP Tool Selection
arXiv CS.AI
•
ArXi:2603.20313v1 Announce Type: cross Large Language Models (LLMs) with tool-calling capabilities have nstrated remarkable potential in executing complex tasks through external tool integration. The Model Context Protocol (MCP) has emerged as a standardized framework for connecting LLMs to diverse toolsets, with individual MCP servers potentially exposing dozens to hundreds of tools.