[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84869-en":3,"doc-seo-84869-105":29,"detail-sidebar-cat-0-en-105":82},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},84869,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",6,"Technology","Agentic AI for IPoDWDM Network Lifecycle Automation MCP Enabled Architecture","Agentic AI for IPoDWDM Network Lifecycle Automation introduces a distributed, vendor-agnostic multi-MCP architecture that drives SDN-based automation and autonomous control across multi-vendor, multi-layer IP-over-DWDM networks. It supports end-to-end service lifecycle automation, closed-loop cross-layer control using a GNPy model and optical telemetry, and is validated on an IPoDWDM testbed. The approach spans physical-layer setup through IP-layer provisioning and performance telemetry monitoring, enabling human-language orchestration of network operations.","Agentic AI for IPoDWDM Network Lifecycle Automation: An  \nMCP-Enabled Architecture  \nChunmin Xia, Jakub Harbaczewski , Nikhil Dsilva , Julie Raulin , Dominic Schneider , Achim Autenrieth  \nAdtran Networks SE, [chunmin.xia@adtran.com](chunmin.xia@adtran.com)  \nAbstract We present a distributed, vendor-agnostic multi-MCP architecture for SDN-based automation and autonomous control of multi-vendor, multi-layer IPoDWDM networks. The framework enables E2E service lifecycle automation, closed-loop cross-layer control using GNPy model and optical telemetry, and is experimentally validated on a IPoDWDM testbed. ©2026 The Authors  \nIntroduction  \nThe rapid development and growing applications of artificial intelligence (AI), together with the explosive growth of different data hungry applications, is accelerating requirements for highly dynamic , deep automation and increasing autonomy imposed on IP-over-DWDM (IPoDWDM) networks. As an universal, standardized interface between autonomous AI agents and the realworld systems, model context protocol (MCP)[1,2] enables scalable and composable development and integration of different kinds of tools indifferent specific domains. Agentic AI application concepts focusing on some specific areas are seen in [3-9] . Based on both simulator/digital twin and real-world test beds, we propose and experimentally demonstrate an MCP-server-based agentic-AI architecture that enables fully automated, vendor-agnostic, multi-layer lifecycle management of IPoDWDM networks, spanning physical-layer setup through IP-layer provisioning and performance telemetry monitoring.  \nNetwork setup and assumptions  \nAs shown schematically in Fig. 1, we consider a representative ring network with at least three network nodes, each comprising ROADMs, variable gain booster and pre-amplifiers as well as couplers/filters, interconnecting coherent pluggables from routers of different vendors including Juniper, Cisco and Arista as well as transponders from Adtran. It is necessary to point out our MCP servers can be easily extended to support anyother routers/transponders with given necessary NETCONF configuration files. The Mosaic Network Controller (MNC), an SDN controller from Adtran, is used as the SDN control platform and is compatible with the available hardware testbed.  \nAI agent and MCP tools development  \nWe have developed our own AI agent based on a Large Language Model (LLM) GPT5 .2. The client prompts are saved in a memory datastore using Redis and attached to the Agent together with any new requests to keep the memory of the context within one session. By evaluating streamable [HTTP-based](HTTP-based) MCP servers and our own agent  \nFig. 1 : Agentic AI assisted IPoDWDM network based on multiple MCP servers  \nagainst commercial agents (e.g. , Copilot, Claude), we identified limitations and iteratively improved our MCP servers and agent.  \nIn considering the importance of security and trustworthiness along with the AI applications , we keep always the harness engineering discipline in mind during developing all the MCP servers. First, all authentication credentials are managed through environment-based configuration parameters for general use cases, while policy-driven Eclipse Dataspace Components Connector (EDCC) [10,11] mechanisms are used to meet higher-level security requirements. Secondly, in order to improve the transparency and ensure a positive user experience , each MCP tool is divided into as many atomic steps as possible , each of which is checked or validated carefully in order to return a clear meaningful information for any conditions even when an unexpected failure occurs.  \nThe MCP servers are developed and tested first of all based on digital twin like Adtran network simulators and then validated in real networks.  \nMulti-MCP server architecture and workflow  \nWe aim to realize a deep smart automation of IPoDWDM network with human language to AI Agent through creating different MCP servers working join","cbCain8FKTmHdsCN","https://ap.wps.com/l/cbCain8FKTmHdsCN","pdf",515650,1,4,"English","en",105,"# Introduction\n# Network setup and assumptions\n# AI agent and MCP tools development\n# Multi-MCP server architecture and workflow\n## Operation automation server\n## Coherent pluggables control server","[{\"question\":\"Which MCP servers are implemented to manage different operational tasks?\",\"answer\":\"The document describes an operation automation server for topology and service orchestration and a coherent pluggables control server for configuration, verification, and post-provisioning performance monitoring end-to-end.\"}]",1784198925,10,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":77,"head_meta":79,"extra_data":81,"updated_unix":27},"agentic-ai-for-ipodwdm-network-lifecycle-automation-mcp-enabled-architecture","",{"@graph":35,"@context":76},[36,52,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/technology/",3,{"item":51,"name":13,"@type":42,"position":21},"https://docshare.wps.com/document/agentic-ai-for-ipodwdm-network-lifecycle-automation-mcp-enabled-architecture/84869/",{"url":51,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":61,"encodingFormat":59,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70],{"name":71,"@type":72,"acceptedAnswer":73},"Which MCP servers are implemented to manage different operational tasks?","Question",{"text":74,"@type":75},"The document describes an operation automation server for topology and service orchestration and a coherent pluggables control server for configuration, verification, and post-provisioning performance monitoring end-to-end.","Answer","https://schema.org",{"og:url":51,"og:type":78,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":80,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":83},[84,88,92,96,101,104,109,114,119,122,125],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":102,"slug":103},50,"technology",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},7,"Healthcare",40,"healthcare",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},8,"Research & Report",30,"research-report",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":28,"slug":124},"Lifestyle","lifestyle",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":97,"slug":128},19,"General","general"]