BridgeScope: A Universal Toolkit for Bridging Large Language Models and Databases
Lianggui Weng, Dandan Liu, Rong Zhu, Bolin Ding, Jingren Zhou

TL;DR
BridgeScope is a universal toolkit that enhances large language models' ability to securely and efficiently interact with databases, improving usability, security, and data transmission in data-driven AI applications.
Contribution
It introduces a modular, security-aware, and database-agnostic framework for LLM-database interaction, with an open-source implementation and novel benchmarks.
Findings
Reduces token usage by up to 80%
Enables more effective database operations by LLMs
Supports data-intensive workflows beyond existing tools
Abstract
As large language models (LLMs) demonstrate increasingly powerful reasoning and orchestration capabilities, LLM-based agents are rapidly proliferating for complex data-related tasks. Despite this progress, the current design of how LLMs interact with databases exhibits critical limitations in usability, security, privilege management, and data transmission efficiency. To resolve these challenges, we introduce BridgeScope, a universal toolkit bridging LLMs and databases through three key innovations. First, it modularizes SQL operations into fine-grained tools for context retrieval, CRUD execution, and ACID-compliant transaction management, enabling more precise and LLM-friendly functionality controls. Second, it aligns tool implementations with both database privileges and user security policies to steer LLMs away from unsafe or unauthorized operations, improving task execution…
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.
