[{"data":1,"prerenderedAt":182},["ShallowReactive",2],{"blog-\u002Fblog\u002F2025\u002F11\u002Fflowfuse+llm+mcp-equals-text-driven-operations":3},{"id":4,"title":5,"body":6,"description":12,"extension":171,"meta":172,"navigation":177,"path":178,"seo":179,"stem":180,"__hash__":181},"blog\u002Fblog\u002F2025\u002F11\u002Fflowfuse+llm+mcp-equals-text-driven-operations.md","FlowFuse + LLM + MCP = Text Driven Operations",{"type":7,"value":8,"toc":163},"minimark",[9,13,16,21,40,48,51,55,58,66,73,89,97,104,108,111,114,117,120,124,131,138,141,144,147],[10,11,12],"p",{},"In industrial operations it's all about getting more out of the CAPEX already\nspent. Achieving higher efficiency means everyone needs to get data from a lot of\ndifferent machines, have an understanding how these machines form lines and fit\ntogether, and holistically understand these as a group of assets that collectively\ncan achieve more.",[10,14,15],{},"With the rapid adoption of Artificial Intelligence (AI), Model Context\nProtocol, low-code platforms it's clear that the future of operations is\nconversational.\nThe interface to machines is becoming plain text, allowing teams to obtain effects\nand scale operational excellence across entire business units simply by asking\nthe right questions.",[17,18,20],"h2",{"id":19},"the-context-challenge","The Context Challenge",[10,22,23,24,29,30,34,35,39],{},"Data capture involves integrating various machine protocols (like\n",[25,26,28],"a",{"href":27},"\u002Fnode-red\u002Fprotocol\u002Fopc-ua\u002F","OPC-UA"," or ",[25,31,33],{"href":32},"\u002Fnode-red\u002Fprotocol\u002Fmodbus\u002F","Modbus","),\ntransporting, combining, and visualizing the information. While low-code tools\nlike Node-RED have decreased the implementation time to mere hours, the full\nproblem isn't solved: what happens ",[36,37,38],"em",{},"after"," the data is collected?",[10,41,42,43,47],{},"Often, raw sensor data—like pressure, voltage, and temperature readings—lacks\ncontext to immediately understand there's a problem worth solving. Even when a dashboard\nhas been built, spotting an issue (such as a high energy consumption on ",[44,45,46],"code",{},"machine 1",")\ndoesn't inherently guide the operator on how to resolve it.\nFurthermore, data flow often involves a psychological hurdle, moving from areas\nwhere an engineer feels comfortable (perhaps the data storage side) to areas of\nless expertise (like machine protocols or physical voltage readings).",[10,49,50],{},"The goal is to asking high-level questions, such as:\n\"What changed in the energy consumption for machine 4?\".",[17,52,54],{"id":53},"text-the-new-language-of-control","Text: The New Language of Control",[10,56,57],{},"Removing code, often a complex layer, can be now achieved because of Large Language\nModels (LLMs) and the Model Context Protocol (MCP).",[10,59,60,61,65],{},"LLMs, like ChatGPT, predict the next word in a sentence, allowing humans to\nquery systems using ",[62,63,64],"strong",{},"natural language"," rather than complex code.\nLLMs face fundamental limitations though: they are typically cloud-based, can be\nslow, and are trained at specific points in time, meaning they cannot inherently\nreact to real-time, event-based data or proprietary local context.",[10,67,68,69,72],{},"This is where the ",[62,70,71],{},"Model Context Protocol (MCP)"," steps in. The promise of\nMCP is to give models more context through an agreed-upon protocol.\nMCP allows operators to define exactly what read-only information (resources) or\nfunctionality (tools) they want to expose to the LLM.",[74,75,76,83],"ul",{},[77,78,79,82],"li",{},[62,80,81],{},"Resources"," are read-only, like sensor readings, employee staff lists, vacation calendars, or specification sheets (e.g., upper and lower temperature limits).",[77,84,85,88],{},[62,86,87],{},"Tools"," are functions that allow the LLM to perform an action or change a state in the physical world.",[10,90,91,92,96],{},"By feeding this context into an MCP server (such as the official ",[25,93,95],{"href":94},"\u002Fnode-red\u002Fflowfuse\u002Fmcp\u002F","FlowFuse MCP node","),\nthe LLM transforms into a powerful operational partner.",[10,98,99,100,103],{},"For example, an operator can ask: \"Can you show me the last five temp sensor readings recorded?\".\nOnce the model identifies an anomaly, the operator can incorporate specifications and ask: \"Are any of these values outside of spec for upper temp or lower temp?\".\nIf a problem is confirmed, the system can use staff and location data to answer a pointed question like: ",[62,101,102],{},"\"Who are all the staff located nearest to the problem, and what is the quickest way to get there?\"",".\nThis capability quickly transforms complex data into actionable steps—finding the problem, comparing it to specs, finding the right person, and routing them to the site—all within a matter of minutes.",[17,105,107],{"id":106},"orchestrating-effects-across-the-machine-fleet","Orchestrating Effects Across the Machine Fleet",[10,109,110],{},"The ability to propagate these text-driven decisions across many machines by the\nsame team is enabled by Node-RED serving as the essential integration layer.",[10,112,113],{},"FlowFuse, a major corporate sponsor of Node-RED, aims to fuse the digital realm\nwith machines and the shop floor for IoT use cases. Node-RED acts as the shell\nthat connects proprietary and legacy machine protocols (OT side) to the modern MCP structure.",[10,115,116],{},"If a manufacturing facility wants to allow an LLM to control a physical device,\nNode-RED can integrate the machine (e.g., a Siemens S7 stack light) and wrap the\ncontrol logic in an MCP tool. The LLM requests an action\n(e.g., \"turn the stack light green\"), the MCP tool sends the action through\nNode-RED's established adapters, and the action is executed.",[10,118,119],{},"This means that existing organizational logic and machine adapters, which have\nalready been integrated into Node-RED, can be instantly made LLM and AI ready.\nThis rapid adaptation allows a very broad spectrum of engineers to be applied to\nproblems, moving past relying on \"tribal knowledge\" held by a single expert.",[17,121,123],{"id":122},"text-driven-playbooks-and-the-human-in-the-loop","Text-Driven Playbooks and the Human in the Loop",[10,125,126,127,130],{},"Looking ahead, this technology enables the creation of ",[62,128,129],{},"text-driven playbooks",".\nAn operator might input a natural language prompt:\n\"How do we optimize a certain procedure in the factory?\". The resulting\noperational procedure, driven by the LLM and executed via MCP tools, becomes a\ndocumented playbook. This system helps organizations achieve operational excellence\nby turning human text input into processes that the rest of the company can read,\nunderstand, and replicate.",[10,132,133,134,137],{},"However, the industry must move cautiously. A critical element of the future of\noperations is the necessity of a ",[44,135,136],{},"human in the loop",".",[10,139,140],{},"AI is predictive and, in certain ways, random, meaning that if context slightly\nchanges, the output is not deterministic. When the consequences of an action are\nphysical or high-stakes\n(e.g., stopping a production line, or an irreversible action like boiling an egg),\nfull control should not be handed over to a non-deterministic system. The risk of\nan AI being \"as confident when they're wrong as when they're right\" necessitates human oversight.",[10,142,143],{},"For the near future (the next five years), the AI acts as a partner or a fault\npartner, making the uncomfortable aspects of complex flows more manageable. It is\ncurrently best applied in reversible or digital tasks, such as generating reports\nor triggering low-consequence actions like turning a stack light orange to signal\nan engineer. As trust grows and impacts iterate, AI will gain more influence and\ncontext, but the final, consequential decisions will remain with the human.",[10,145,146],{},"The combination of LLMs, MCP, and Node-RED provides operators with super powers.\nThe operational floor is transforming from a place where experts write complex\ncode for singular machines, to a conversational environment where high-level, natural\nlanguage queries drive intelligent, scalable actions across the entire enterprise.",[10,148,149,150,156,157,162],{},"Ready to experience text-driven operations in your own facility?\n",[25,151,155],{"href":152,"rel":153},"https:\u002F\u002Fapp.flowfuse.com\u002Faccount\u002Fcreate",[154],"nofollow","Try FlowFuse for free"," or request a personalized demo to see how LLM-powered automation can transform your industrial processes.\n",[25,158,161],{"href":159,"rel":160},"https:\u002F\u002Fflowfuse.com\u002Fcontact-us\u002F",[154],"Contact us today"," or sign up for our upcoming webinar to stay ahead in the Industry 4.0 revolution.",{"title":164,"searchDepth":165,"depth":165,"links":166},"",2,[167,168,169,170],{"id":19,"depth":165,"text":20},{"id":53,"depth":165,"text":54},{"id":106,"depth":165,"text":107},{"id":122,"depth":165,"text":123},"md",{"navTitle":5,"excerpt":173},{"type":7,"value":174},[175],[10,176,12],{},true,"\u002Fblog\u002F2025\u002F11\u002Fflowfuse+llm+mcp-equals-text-driven-operations",{"title":5,"description":12},"blog\u002F2025\u002F11\u002Fflowfuse+llm+mcp-equals-text-driven-operations","xdB6fFTS51NwwjbtUlYmi7aSeZKF-L9Me2c7pzfrP20",1780070553764]