DiffusionData, a provider of a secure, real-time data server that powers personalised experiences on mobile, web and AI platforms, today announced the launch of an open source implementation of the Model Context Protocol (MCP) that lets AI assistants interact with Diffusion in real-time. The Diffusion MCP Server enables users to explore, create and configure topics and topic views through natural language, guided by a contextual help system that explains concepts, shows syntax, executes operations, and interprets results. The MCP Server is the first Agentic AI feature delivered by DiffusionData and can be downloaded here.
The Diffusion MCP Server connects LLM AI assistants, such as Claude, to Diffusion making rich APIs and documentation considerably easier to work with. For Ops teams, it enables conversational operations and monitoring - query sessions, list topics, inspect metrics, create metric collectors on the fly - while enforcing safeguards and providing straightforward setup for local or remote servers.
The Future of Real-Time Data Streaming
With open protocols like the Modern Context Protocol (MCP) and AgentToAgent (A2A) setting common interfaces for tool access and inter-agent coordination, real-time data becomes the bedrock of Agentic AI; agents must act on continuously refreshed context rather than batch snapshots from data sources, and from each other.
Grethe Brown, CEO of DiffusionData, said: “The real-time data streaming market is undergoing a fundamental shift, from a technical enabler to a business imperative. In a world increasingly powered by AI and edge intelligence, the ability to process and act on data the moment it’s created is now essential. AI agents amplify this advantage by continuously learning from real-time signals, automating responses, and turning streams of raw information into actionable insight that drives growth and resilience.”
Use Cases
The Diffusion MCP Server has two distinct use case scenarios.
The Diffusion MCP Server has two distinct use case scenarios.
- Firstly, as a development tool. It effectively turns your AI assistant into a Diffusion consultant who doesn't just explain things but actually shows you how they work. Your AI assistant gets a thorough understanding of Diffusion concepts through the MCP Server's contextual help system, which covers topics, sessions, metrics, and topic views. For developers new to Diffusion, the MCP Server is particularly useful. You can explore the topic tree structure, play around with topic selectors, try different configurations, and see what various properties do (all through conversation).
- Secondly, it has operations and monitoring capabilities. In Ops, for example, the MCP Server becomes a handy monitoring and diagnostic tool. System administrators and DevOps teams can interact with live Diffusion servers using natural language, analysing metrics into straightforward questions. The MCP Server is particularly effective at one-off analysis; create session metric collectors on the fly to monitor specific user groups, set up topic metric collectors to track performance of critical data paths, or query time series topics to analyse historical patterns. All without writing any code. What makes the Diffusion MCP Server genuinely valuable is its contextual help system. Your AI assistant doesn't just blindly run commands, it understands how Diffusion works, as well as best practices, and common patterns.
Real-World Examples
iGaming: your sportsbook uses Diffusion to stream live odds and handle real-time bets. During a major event, some users are getting delayed updates. You ask your AI assistant: “show me sessions grouped by country and connection type.” Within seconds, you can see that mobile users in certain regions are on slower transports protocols. Your assistant then helps you create a metric collector for that segment and sets up alerts if latency gets too high.
iGaming: your sportsbook uses Diffusion to stream live odds and handle real-time bets. During a major event, some users are getting delayed updates. You ask your AI assistant: “show me sessions grouped by country and connection type.” Within seconds, you can see that mobile users in certain regions are on slower transports protocols. Your assistant then helps you create a metric collector for that segment and sets up alerts if latency gets too high.
Financial Trading: you're building a new trading application. You ask: “help me understand topic views and create one that filters market data based on asset class.” Your AI assistant explains the topic view DSL, shows you examples, helps you write the specification, creates the view, and then helps you test it by fetching data through it.
IoT Sensor Network: thousands of sensors are publishing data. You need to find unresponsive nodes. You ask your AI assistant: “show me the structure of my sensor topics and identify any that aren't publishing data.” Your AI assistant explores your topic tree, works out the hierarchical structure, and helps you create targeted queries to find silent sensors.
Safety and Common Sense
The MCP Server includes sensible safeguards. For destructive operations like removing topics, your AI assistant will always show you exactly what will be affected and ask for confirmation. It understands the potential impact of broad topic selectors and will steer you toward safer, more specific operations.
The MCP Server includes sensible safeguards. For destructive operations like removing topics, your AI assistant will always show you exactly what will be affected and ask for confirmation. It understands the potential impact of broad topic selectors and will steer you toward safer, more specific operations.
Getting Started
Setting up the Diffusion MCP Server is straightforward (full instructions are in the project's README). Once configured, your MCP-compatible AI assistant can connect to your Diffusion server (local or remote), and you're ready to explore, monitor, and manage your real-time data infrastructure through conversation.
Setting up the Diffusion MCP Server is straightforward (full instructions are in the project's README). Once configured, your MCP-compatible AI assistant can connect to your Diffusion server (local or remote), and you're ready to explore, monitor, and manage your real-time data infrastructure through conversation.
Brown concluded: “Ultimately, our goal is to build the real-time nervous system for intelligent enterprises. In a world driven by domain-specific AI models and autonomous agents, continuous, contextual data flow will define the next era of business intelligence, enabling organizations not just to react, but to act instantly.”
DiffusionData supplies real-time context with event-driven pub/sub, delta streaming, flow control, and hierarchical topics, reducing payloads and latency while keeping autonomous workflows synchronized with real-world change. It is used by companies worldwide in sectors such as financial services, iGaming, retail, travel and transportation, , and digital media. It is purpose-built to simplify and speed data-driven, real-time application development, reduce operational costs, and economically deliver personalised data.
To watch a brief demonstration of DiffusionData’s MCP Server capabilities, click here.
