Optimizing FaaS Platforms for MCP-enabled Agentic Workflows

2026-01-21

AI Summary

Deploying multi-agent workflows on serverless platforms faces significant challenges in state management and scalability. This work proposes FAME, an architecture that decouples agent paradigms such as ReAct into three composable Function-as-a-Service (FaaS) components—Planner, Actor, and Evaluator—orchestrated via AWS Step Functions and built upon LangGraph. To overcome the inherent statelessness of FaaS, FAME introduces automated memory persistence, Lambda-based encapsulation of Model Context Protocol (MCP) servers, tool output caching, and function fusion strategies. Experimental results on paper summarization and log analysis tasks demonstrate that FAME achieves up to a 13× reduction in latency, an 88% decrease in input tokens, and a 66% cost saving, while substantially improving workflow completion rates.

Technology Category

• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Agentic workflows that use autonomous AI Agents powered by Large Language Models (LLMs) and Model Context Protocol (MCP) servers is rapidly rising. This introduces challenges in scalable cloud deployment and state management. Traditional hosting on Virtual Machines (VMs) is resource-intensive and lacks elasticity. Functions-as-a-Service (FaaS) platforms offer modularity, autoscaling and cost efficiency but are inherently stateless. In this paper, we present the FAME, a FaaS-based architecture for orchestrating MCP-enabled agentic workflows. FAME decomposes agentic patterns such as ReAct into composable agents: Planner, Actor and Evaluator, that are each a FaaS function built using LangGraph and are orchestrated as a FaaS workflow. This enables modular composition as AWS Step Functions and avoids function timeouts seen for monolithic agentic workflows. To address context persistence across user requests in a conversation, FAME automates agent memory persistence and injection using DynamoDB. It also optimizes MCP server deployment through AWS Lambda wrappers, caches tool outputs in S3 and proposes function fusion strategies. We evaluate FAME on two representative applications, on research paper summarization and log analytics, under diverse memory and caching configurations. Results show up to 13x latency reduction, 88% fewer input tokens and 66% in cost savings, along with improved workflow completion rates. This demonstrates the viability of serverless platforms for hosting complex, multi-agent AI workflows at scale.

Problem

• FaaS
• Agentic Workflows
• MCP
• State Management
• Serverless

Innovation

• FaaS
• MCP
• Agentic Workflows
• Serverless Architecture
• Context Persistence