ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents
Elias Lumer, Anmol Gulati, Vamse Kumar Subbiah, Pradeep Honaganahalli Basavaraju, James A. Burke

TL;DR
ScaleMCP introduces a dynamic, auto-synchronizing tool selection framework for LLM agents that enhances tool management, retrieval, and interaction capabilities, significantly improving performance in multi-turn, tool-rich environments.
Contribution
It presents ScaleMCP, a novel approach with a retriever and auto-synchronizing storage system, enabling autonomous, dynamic tool management for LLM agents, and introduces the TDWA embedding strategy.
Findings
Improved tool retrieval accuracy across multiple LLM and embedding models.
Enhanced agent invocation performance in dynamic tool environments.
Effective scalability demonstrated on a dataset of 5,000 MCP servers.
Abstract
Recent advancements in Large Language Models (LLMs) and the introduction of the Model Context Protocol (MCP) have significantly expanded LLM agents' capability to interact dynamically with external tools and APIs. However, existing tool selection frameworks do not integrate MCP servers, instead relying heavily on error-prone manual updates to monolithic local tool repositories, leading to duplication, inconsistencies, and inefficiencies. Additionally, current approaches abstract tool selection before the LLM agent is invoked, limiting its autonomy and hindering dynamic re-querying capabilities during multi-turn interactions. To address these issues, we introduce ScaleMCP, a novel tool selection approach that dynamically equips LLM agents with a MCP tool retriever, giving agents the autonomy to add tools into their memory, as well as an auto-synchronizing tool storage system pipeline…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Artificial Intelligence in Law
