Pith. sign in

REVIEW 8 cited by

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.03275 v1 pith:WP3SBP3E submitted 2025-05-06 cs.AI cs.SE

RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation

classification cs.AI cs.SE
keywords rag-mcptoolpromptselectionbloatexternalgenerationllms
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Mitigating Errors in LLM-Generated Web API Invocations via Retrieval-Augmented Generation and Constrained Decoding

    cs.SE 2026-07 conditional novelty 6.0

    Constrained decoding derived from OpenAPI specifications eliminates hallucinated web API calls in LLM-generated code and substantially improves correctness across 24 models, while retrieval-augmented generation yields...

  2. MCP Server Architecture Patterns for LLM-Integrated Applications

    cs.SE 2026-06 unverdicted novelty 6.0

    Catalogues five MCP server architectural patterns observed across fifteen servers, plus anti-patterns and quantitative measurements on tool handling and overhead.

  3. ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents

    cs.AI 2026-06 unverdicted novelty 6.0

    CMTF is a causal filtering method that reduces tool exposure to one per step while matching baseline success rates and cutting token use by ~90% in 102-task benchmarks with 100 tools.

  4. How Many Tools Should an LLM Agent See? A Chance-Corrected Answer

    cs.IR 2026-05 unverdicted novelty 6.0

    Bits-over-Random (BoR) is a chance-corrected metric for tool shortlist evaluation that enables query-adaptive depth selection via RL, matching fixed-list coverage with shorter lists on BFCL and ToolBench.

  5. More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries

    cs.SE 2026-05 unverdicted novelty 6.0

    Skill shadowing, not context overhead, is the dominant cause of performance degradation when LLM agent skill libraries expand.

  6. ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox

    cs.AI 2026-05 unverdicted novelty 6.0

    ComplexMCP benchmark shows current LLM agents achieve at most 60% success on interdependent tool tasks versus 90% for humans, due to tool retrieval saturation, over-confidence, and strategic defeatism.

  7. ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox

    cs.AI 2026-05 unverdicted novelty 6.0

    ComplexMCP benchmark shows top LLM agents achieve under 60% success on dynamic interdependent tool tasks versus 90% for humans, due to tool retrieval saturation, over-confidence, and strategic defeatism.

  8. Scaling Enterprise Agent Routing: Degradation, Diagnosis, and Recovery

    cs.CL 2026-06 unverdicted novelty 4.0

    Routing F1 for under-specified requests drops 16-23pp as agent catalog scales to 110, but embedding shortlisting recovers 10-17pp on a 584-tool enterprise system.