paper-with-me

홈 › Papers

MCP Bridge: A Lightweight, LLM-Agnostic RESTful Proxy for Model Context Protocol Servers

2025-04-11 · Arash Ahmadi, Sarah Sharif, Yaser M. Banad

Large Language Models (LLMs) are increasingly augmented with external tools through standardized interfaces like the Model Context Protocol (MCP). However, current MCP implementations face critical limitations: they typically require local process execution through STDIO transports, making them impractical for resource-constrained environments like mobile devices, web browsers, and edge computing. We present MCP Bridge, a lightweight RESTful proxy that connects to multiple MCP servers and exposes their capabilities through a unified API. Unlike existing solutions, MCP Bridge is fully LLM-agnostic, supporting any backend regardless of vendor. The system implements a risk-based execution model with three security levels standard execution, confirmation workflow, and Docker isolation while maintaining backward compatibility with standard MCP clients. Complementing this server-side infrastructure is a Python based MCP Gemini Agent that facilitates natural language interaction with MCP tools. The evaluation demonstrates that MCP Bridge successfully addresses the constraints of direct MCP connections while providing enhanced security controls and cross-platform compatibility, enabling sophisticated LLM-powered applications in previously inaccessible environments

📄 PDF Abstract BibTeX arXiv:2504.08999

Code (0)

등록된 구현이 없습니다.

Tasks

Edge-computing

Similar Papers 제목 키워드 기반

ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference

2026-05-09 · Junjie Li, Jiong Lou, Jie Li arxiv

Efficient long-context inference in Large Language Models (LLMs) is severely constrained by the Key-Value (KV) cache memory wall, yet existing pruning methods force a choice between low-latency heuristics that sacrifice …

FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion

2026-04-21 · Tao Fan, Guoqiang Ma, Yuanfeng Song, Lixin Fan 외 arxiv

Federated fine-tuning of Large Language Models (LLMs) is obstructed by a trilemma of challenges: protecting LLMs intellectual property (IP), ensuring client privacy, and mitigating performance loss on heterogeneous data.…

Sentinel: Attention Probing of Proxy Models for LLM Context Compression with an Understanding Perspective

2025-05-29 · Yong Zhang, Yanwen Huang, Ning Cheng, Yang Guo 외

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external context, but retrieved passages are often lengthy, noisy, or exceed input limits. Existing compression methods typically require su…

DecoderRAGRetrieval-augmented GenerationSentence

Sharing annotations better: RESTful Open Annotation

2015-07-01 · IJCNLP 2015 7 · Sampo Pyysalo, Jorge Campos, Juan Miguel Cejuela, Filip Ginter 외

Beyond Perplexity: A Behavioral Evaluation Framework for Deployment-Memory Claims in LLM Test-Time Training

2026-07-01 · Xiangchen Song, Zhenhao Chen, Lingjing Kong, Shaoan Xie 외 arxiv

Large language model test-time training (TTT) is often evaluated through local proxy metrics: models are updated on recent tokens, retrieved context, target-domain data, or verifiable task attempts, and then judged by pe…

Domain Adaptation