Metraipolis › archive › dc_4fae8bc92c01
LLM within MCP Matters: Measuring Inefficient Resource Utilization Driven by LLMs — arXiv:2608.08467
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.08467
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:50:47.969Z
- SHA-256 of the archived text
f64f9862aea4ff92a09623b5ec96e6f76398eda9d27cdd7f9a55e85e0a5edf69- Stable URL of this page
https://metraipolis.com/documento/dc_4fae8bc92c01
How to cite
LLM within MCP Matters: Measuring Inefficient Resource Utilization Driven by LLMs — arXiv:2608.08467 — arXiv (en), https://arxiv.org/abs/2608.08467 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4fae8bc92c01 (Metraipolis archive dc_4fae8bc92c01, sha256 f64f9862aea4ff92a09623b5ec96e6f76398eda9d27cdd7f9a55e85e0a5edf69)
BibTeX
@misc{dc4fae8bc92c01,
title = {LLM within MCP Matters: Measuring Inefficient Resource Utilization Driven by LLMs — arXiv:2608.08467},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.08467},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4fae8bc92c01; sha256 f64f9862aea4ff92a09623b5ec96e6f76398eda9d27cdd7f9a55e85e0a5edf69},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08467. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The Model Context Protocol (MCP) standardizes how servers expose data and tools to Large Language Models (LLMs). A common server design embeds frequently used reference data, such as identifier lookup tables, directly in the server instructions: the system-prompt text a server hands to the host application. When a query concerns an entry of the embedded table, the model can act on it immediately instead of re-discovering the same information through a search tool. We test whether client LLMs actually consume such instruction-embedded data, reporting a 54,000-trial study across 24 LLMs (9 Claude, 6 Gemini, 9 GPT) on a production legal-information MCP server. A diagnostic condition that removes the competing search tool shows that failures are dominated by behavioral preference rather than missing capability. With search unavailable, 23 of 24 models read the embedded data reliably (hit ratio at least 98%); with a search tool merely present, 9 models drop below 15%. A 2^3 factorial analysis of three instruction-level interventions reveals strong interaction effects: combining all three restores at least 86% for 20 of 24 models, but individual interventions can backfire for specific model families. Per-server prompt engineering is therefore a workaround rather than a fix; we argue that MCP host applications should provide an explicit mechanism that places server instructions ahead of tool selection in the client LLM's deliberation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2608.08467 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T08:49:41.984Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).