Network and Systems Performance Characterization of MCP-Enabled LLM Agents
On the map: LLM agents and tool use → Tool learning and function calling
Abstract (arXiv)
Model Context Protocol (MCP) has recently gained increased attention within the AI community for providing a standardized way for large language models (LLMs) to interact with external tools and services, significantly enhancing their capabilities. However, the inclusion of extensive contextual information, including system prompts, MCP tool definitions, and context histories, in MCP-enabled LLM interactions, dramatically inflates token usage. Given that LLM providers charge based on tokens, these expanded contexts can quickly escalate monetary costs and increase the computational load on LLM services. This paper presents a comprehensive measurement-based analysis of MCP-enabled interactions with LLMs, revealing trade-offs between capability, performance, and cost. We explore how different LLM models and MCP configurations impact key performance metrics such as token efficiency, monetary cost, task completion times, and task success rates, and suggest potential optimizations, including enabling parallel tool calls and implementing robust task abort mechanisms. These findings provide useful insights for developing more efficient, robust, and cost-effective MCP-enabled workflows.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 6 of its 18 references that are in the map. First posted on arXiv 20 Oct 2025.
Builds on
6 of 18 references.
References · 6
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
- 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
- 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignmentcited by 721
- 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 629
- 2023LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Datasetcited by 461
- 2023Stateful Large Language Model Serving with Pensievecited by 61
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language Models
- 2025MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools
- 2025MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
- 2026Understanding How Enterprises Adopt the Model Context Protocol for LLM-Driven Software Engineering
- 2025ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents
- 2025Survey of LLM Agent Communication with MCP: A Software Design Pattern Centric Review
- 2026Enhancing Model Context Protocol (MCP) with Context-Aware Server Collaboration
- 2025MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers