RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909602304491520 |
|---|---|
| author | Gan, Tiantian Sun, Qiyao |
| author_facet | Gan, Tiantian Sun, Qiyao |
| contents | Large language models (LLMs) struggle to effectively utilize a growing number of external tools, such as those defined by the Model Context Protocol (MCP)\cite{IntroducingMCP}, due to prompt bloat and selection complexity. We introduce RAG-MCP, a Retrieval-Augmented Generation framework that overcomes this challenge by offloading tool discovery. RAG-MCP uses semantic retrieval to identify the most relevant MCP(s) for a given query from an external index before engaging the LLM. Only the selected tool descriptions are passed to the model, drastically reducing prompt size and simplifying decision-making. Experiments, including an MCP stress test, demonstrate RAG-MCP significantly cuts prompt tokens (e.g., by over 50%) and more than triples tool selection accuracy (43.13% vs 13.62% baseline) on benchmark tasks. RAG-MCP enables scalable and accurate tool integration for LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_03275 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation Gan, Tiantian Sun, Qiyao Artificial Intelligence Software Engineering Large language models (LLMs) struggle to effectively utilize a growing number of external tools, such as those defined by the Model Context Protocol (MCP)\cite{IntroducingMCP}, due to prompt bloat and selection complexity. We introduce RAG-MCP, a Retrieval-Augmented Generation framework that overcomes this challenge by offloading tool discovery. RAG-MCP uses semantic retrieval to identify the most relevant MCP(s) for a given query from an external index before engaging the LLM. Only the selected tool descriptions are passed to the model, drastically reducing prompt size and simplifying decision-making. Experiments, including an MCP stress test, demonstrate RAG-MCP significantly cuts prompt tokens (e.g., by over 50%) and more than triples tool selection accuracy (43.13% vs 13.62% baseline) on benchmark tasks. RAG-MCP enables scalable and accurate tool integration for LLMs. |
| title | RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation |
| topic | Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2505.03275 |