MCP-Zero: Active Tool Discovery for Autonomous LLM Agents

Current LLM agents inject thousands of tool schemas into prompts, creating massive context overhead and reducing models to passive tool selectors rather than autonomous agents. We introduce MCP-Zero, an active agent framework that restores tool discovery autonomy to LLMs themselves. Instead of overwhelming models with all available tools, MCP-Zero enables agents to actively identify capability gaps, and request specific tools on-demand, transforming them from large-scale retrievers into genuine autonomous agents. The framework operates through three core mechanisms: (1) Active Tool Request, where models autonomously generate structured requests specifying their exact tool requirements; (2) Hierarchical Semantic Routing, a two-stage algorithm that matches requests to relevant servers and tools through improved semantic alignment; (3) Iterative Capability Extension, enabling agents to progressively build cross-domain toolchains while maintaining minimal context footprint. We also construct MCP-tools, a comprehensive dataset of 308 MCP servers and 2,797 tools from the official Model-Context-Protocol repository. Experiments demonstrate that MCP-Zero preserves agent autonomy while achieving substantial efficiency gains: (i) accurate tool selection from nearly 3k candidates across 248.1k tokens; (ii) 98\% reduction in token consumption on APIBank while maintaining high accuracy; and (iii) consistent multi-turn performance that scales with tool ecosystem growth. This work establishes active tool discovery as a fundamental design pattern for scalable autonomous agent systems.

@article{fei2025_2506.01056,
  title={ MCP-Zero: Active Tool Discovery for Autonomous LLM Agents },
  author={ Xiang Fei and Xiawu Zheng and Hao Feng },
  journal={arXiv preprint arXiv:2506.01056},
  year={ 2025 }
}