[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84039-en":3,"doc-seo-84039-105":29,"detail-sidebar-cat-0-en-105":89},{"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":4,"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},84039,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",6,"Technology","MCP Enabled Agentic AI for Autonomous IPoDWDM Network Lifecycle Automation","An MCP-enabled agentic AI architecture enables autonomous, vendor-agnostic control of IPoDWDM networks through multi-layer, end-to-end lifecycle automation. The system coordinates an LLM-driven agent with multiple HTTP-based MCP servers and uses NETCONF/SNMP or TAPI to interact with network elements and optical SDN controllers. Live closed-loop automation is demonstrated with GNPy-based performance estimation and telemetry visualization, validated on a simulator/digital twin and a real testbed.","MCP-Enabled Agentic AI for Autonomous IPoDWDM Net  \nwork Lifecycle Automation  \nChunmin Xia, Jakub Harbaczewski , Nikhil Dsilva , Julie Raulin , Dominic Schneider , Achim Autenrieth  \nAdtran Networks SE, [chunmin.xia@adtran.com](chunmin.xia@adtran.com)  \nAbstract This demo presents an MCP-enabled agentic AI architecture for autonomous control of vendor-agnostic IPoDWDM networks. We demonstrate live end-to-end lifecycle multi-layer automation and closed-loop control using GNPy and telemetry, validated on a real testbed. ©2026 The Authors  \nOverview  \nIncreasing demand from AI workloads and highbandwidth services is reshaping optical networks from traditional layered transport models and embedded optics toward next generation converged IPoDWDM infrastructures , enabled by highspeed single-channel rates such as 400G/800G coherent pluggables. The state of the art of IPoDWDM orchestrator uses a hierarchical controller to synchronize IP and optical SDN controllers[1,2] . However, this approach becomes complicated and hence expensive when multi-vendors located in different areas from both IP and optical networks are involved. In particular, achieving full automation for IPoDWDM control introduces significant complexity, as it requires tight vertical integration across network layers as well as horizontal integration across multiple vendors and heterogeneous control systems, posing challenges for cost-effective implementation.  \nIn parallel, the explosive growth of agentic AI is widely regarded as a potential breakthrough for achieving universal and scalable automation [3- 7] . Secondly, as a standardized interface between autonomous AI agents and real-world systems, model context protocol (MCP) [8 ,9] enables scalable and composable development and integration of different kinds of tools for various specific domains.  \nTherefore, in this demo, as shown in Fig. 1, we propose, implement, and demonstrate an MCP server-based agentic AI architecture, validated using both a simulator/digital twin and realworld testbeds. The proposed solution enables fully automated, vendor-agnostic, multi-layer lifecycle management of IPoDWDM networks, spanning physical layer setup through IP layer provisioning and performance telemetry monitoring.  \nLLM-Powered Agentic Control Framework for IPoDWDM via MCP Servers  \n| Plug & device control server Show interface Show pluggable Show\u003Cbr>configuration Configure & verify Performance\u003Cbr>metric\u003Cbr>NETCONF\u003Cbr>CLI\u003Cbr>\u003Cbr>\u003Cbr>Show/plot physical route & connections Estimate path performance Show/plot path OSNR & power\u003Cbr>\u003Cbr>TAPI\u003Cbr>\u003Cbr>Performance GNPy server\u003Cbr> TAPI/RestAPI\u003Cbr> TAPI\u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr> NETCONF/SNMP |  |  |  |\n| --- | --- | --- | --- |\n|  | Physical devices: routers & pluggables, ROADMs, amplifiers, transponders, filters |  |  |\n|  |  • Adtran ensemble simulator based network \u003Cbr>\u003Cbr>• Adtran real testbed based network |  |  |\n\nFig. 1 : Workflow and architecture of MCP servers based agentic IPoDWDM network  \nAs illustrated in Fig. 1, an LLM (e.g. GPT-5.2) based AI agent coordinates multiple streamable [HTTP-based MCP servers](HTTP-based MCP servers), each hosting a collection of MCP tools. These servers interact either directly with network elements, such as routers, or through the Transport API (TAPI) with optical SDN controllers that interface with the underlying network via SNMP or NETCONF. MCP servers are described briefly as follows:  \n1. Plug & device control server: Check, configure and verify the coherent pluggables of routers or transponders. Performance metrics (e.g. BER and OSNR) are monitored and visualized after service provisioning.  \n2. Operation automation server: Visualize network topology including detailed nodes, shelves, cards and ports as well as fiber connections. Multiple fiber maps can be created or removed in batch using a single prompt.  \n3. Service provisioning server: Three MCP tools enable service provisioning via (1) stepby-step ROADM-based configuration by using cloud-ba","cbCaivKIkEdoMoOj","https://ap.wps.com/l/cbCaivKIkEdoMoOj","pdf",682335,1,4,"English","en",105,"# Overview\n# LLM-Powered Agentic Control Framework for IPoDWDM via MCP Servers\n## Plug & device control server\n## Operation automation server\n## Service provisioning server\n## Performance GNPy server\n## Telemetry & Visualization server\n# Innovation","[{\"question\":\"What problem does the MCP-enabled agentic AI architecture address for IPoDWDM networks?\",\"answer\":\"It targets the high complexity and cost of full automation when IP and optical control must be tightly integrated across layers and coordinated across multiple vendors and heterogeneous systems.\"},{\"question\":\"How does the proposed system coordinate the AI agent with network control?\",\"answer\":\"An LLM-based agent orchestrates multiple HTTP-based MCP servers, which provide MCP tools that interact directly with network elements or via TAPI with optical SDN controllers using SNMP/NETCONF.\"},{\"question\":\"What capabilities are covered by the different MCP servers in the framework?\",\"answer\":\"They cover coherent pluggable checking/configuration and verification, topology visualization and batch fiber map changes, ROADM-based and end-to-end service provisioning, GNPy-compatible optical performance estimation, and telemetry retrieval/visualization from a time-series database.\"}]",1784192177,10,{"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":84,"head_meta":86,"extra_data":88,"updated_unix":27},"mcp-enabled-agentic-ai-for-autonomous-ipodwdm-network-lifecycle-automation","",{"@graph":35,"@context":83},[36,52,66],{"@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/mcp-enabled-agentic-ai-for-autonomous-ipodwdm-network-lifecycle-automation/84039/",{"url":51,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"What problem does the MCP-enabled agentic AI architecture address for IPoDWDM networks?","Question",{"text":73,"@type":74},"It targets the high complexity and cost of full automation when IP and optical control must be tightly integrated across layers and coordinated across multiple vendors and heterogeneous systems.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"How does the proposed system coordinate the AI agent with network control?",{"text":78,"@type":74},"An LLM-based agent orchestrates multiple HTTP-based MCP servers, which provide MCP tools that interact directly with network elements or via TAPI with optical SDN controllers using SNMP/NETCONF.",{"name":80,"@type":71,"acceptedAnswer":81},"What capabilities are covered by the different MCP servers in the framework?",{"text":82,"@type":74},"They cover coherent pluggable checking/configuration and verification, topology visualization and batch fiber map changes, ROADM-based and end-to-end service provisioning, GNPy-compatible optical performance estimation, and telemetry retrieval/visualization from a time-series database.","https://schema.org",{"og:url":51,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":90},[91,95,99,103,108,111,116,121,126,129,132],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":109,"slug":110},50,"technology",{"id":112,"doc_module":4,"doc_module_name":45,"category_name":113,"show_sort_weight":114,"slug":115},7,"Healthcare",40,"healthcare",{"id":117,"doc_module":4,"doc_module_name":45,"category_name":118,"show_sort_weight":119,"slug":120},8,"Research & Report",30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":130,"show_sort_weight":28,"slug":131},"Lifestyle","lifestyle",{"id":133,"doc_module":4,"doc_module_name":45,"category_name":134,"show_sort_weight":104,"slug":135},19,"General","general"]