Fusion MCP Server Is Now Released & Open Source
There’s a narrow band between “AI demo” and “actually useful in production,” and most tools miss it by a country mile. Fusion MCP Server doesn’t. Now that it’s open source, MCP-compatible AI assistants get a controlled bridge into Everpure FlashArray and FlashBlade environments, one built to answer real operational questions about fleet inventory, capacity, performance, alerts, volumes, file systems, workloads, and presets, without turning your storage estate into a science fair project. The AI Agent doesn’t get to vibe its way through your infrastructure. It works through a clean tool surface backed by real Everpure APIs, and writes stay hidden until you flip them on yourself. What it actually solves If you’ve ever wanted to ask a storage question in plain English and get something better than a dashboard scavenger hunt, this is that. Fusion MCP Server sits between your AI agent and your arrays: the assistant talks to the server, the server authenticates with configured array API tokens, calls supported Everpure APIs, and returns structured results. Your assistant never touches the arrays directly. Practically, that means engineers can ask things like: Show me the fleet overview Which arrays have capacity concerns Show array performance for the last 24 hours List workload presets available in this fleet Show active alerts with remediation links The data was never the problem. Storage teams already have it. What eats the day is bouncing between menus, tabs, and API docs just to answer something like “which arrays are closest to full?” Think of it like swapping a pile of ad hoc curl commands and tribal knowledge for a typed interface your AI assistant can reason over. Calling it “screen scraping with confidence” undersells it. It behaves more like a junior SRE who actually reads the schema. Why engineers should care The release leads with reads, which is exactly the right default for infrastructure tooling. Out of the box, Fusion MCP Server covers fleet overview, capacity and performance, storage objects, configuration audit, and optional supervised actions for placement recommendations, preset creation and updates, and workload deployment. A few details stand out: It works with FlashArray and FlashBlade environments in a Fusion fleet, including mixed environments, as long as you provide at least one token for each platform type for Remote Execution. If the API version you have on your arrays does not yet have the endpoints with Remote Execution capability enabled, you must supply an API token for every array in the fleet. More on that in the next section. Fleet discovery covers the supported read workflows broadly, though some, especially performance, still need a direct token for each array you want to query. Built-in prompts handle fleet, performance, and config workflows, and it also works through plain natural-language questions if your agent doesn’t expose MCP prompts directly. Read-only endpoint documentation plus a whitelisted authenticated GET fetch tool cover supported API surface beyond the dedicated tools. Let’s talk Tokens first Back in Purity REST API version 2.38, Everpure started to include a capability for API endpoints called Remote Execution. This is the mechanism that lets a client invoke a Purity REST API request on a different fleet member, and that request executes as though it were initiated locally on that remote member. The catch is that both arrays must have the same API version available on them as well as the endpoint being executed against must have Remote Execution capability. As of today, not all endpoints have this capability, so there must be an API token specified for each array in the fleet until they have all been enabled. We are diligently working to get all endpoints enabled to make this easier for everyone. Stay tuned! Installation (that does not require a PhD) The setup flow is refreshingly direct: Download the latest binary from GitHub Releases or build from source. Generate API tokens for the arrays you want to query. Run generate-config with your FlashArray and/or FlashBlade targets. Drop the generated config into your MCP-capable agent using the standard start --auth-config pattern over STDIO. generate-config does more than write boilerplate. It validates tokens, detects each array’s API version, resolves array names, and writes the auth config with restrictive permissions: the config directory gets 0700 and the file gets 0600. Want an even easier way? How you just tell your AI Agent to “Read this repository at https://github.com/PureStorage-OpenConnect/fusion-mcp-server and the included USER_GUIDE.md file and add the Fusion MCP server to this agent.” Easy-peasy as it’ll step you thought the process and create the config file for you. A few caveats are worth flagging before you point this at anything that matters: The published binaries aren’t signed, so macOS and Windows may throw a warning on first run. Build from source if that’s a dealbreaker. It’s all there, have at it! Keep the generated auth-config.json local, don’t share it, and rotate tokens if one ever leaks. None of that is friction. It’s the fine print you’d want before trusting a tool with API tokens. Supervised write actions: powerful, optional, and very much not on by default Now for the part everyone asks about first, and the part some people should absolutely not enable first: write actions. Fusion MCP Server hides write tools by default. You turn them on explicitly, either during config generation with --enable-write-tools or later with update-config --enable-write-tools. Enabled, the supervised actions cover these processes with more to come as the product evolves: Placement recommendations Workload preset creation Workload preset updates Workload deployment The approval step is the clever bit. Write operations sit behind an explicit confirmation. If the agent supports MCP Elicitation, the server pops up an interactive dialog for every write tool, so you can review the proposed action and approve or decline before anything changes. If the agent doesn’t support Elicitation, it falls back to telling the agent, in plain instructions, to ask you for approval before resubmitting the call. One practical wrinkle: the write tools inherit whatever permissions live on the API tokens you configure, so the workflow only works if those tokens can perform the write. So when should you flip the switch? Enable write tools if you want supervised acceleration on repeatable workflows: placing a workload from a known preset, updating a policy-backed preset, or turning a natural-language request into a deployment action that still needs a human to sign off. Skip it if you’re still validating token scope, using the server mainly for observability, or introducing MCP to a team that hasn’t built trust in the read-only workflows yet. Start with read-only. Make it boring. Then decide whether supervised writes are the next move. Write tools toggle on and off with a simple update-config command, so this isn’t a one-way door: turn them off again anytime with update-config --enable-write-tools=false. Use cases that actually matter This release isn’t for people who like screenshots of AI chats. It’s for engineers and operators who want faster answers and safer workflows. A few obvious wins: Fleet triage Ask for a fleet overview with alerts, array inventory, Purity version, and fleet connections, the kind of first-response context you want before guessing which dashboard to open. Capacity and performance review Ask which configured arrays have the highest used capacity, which have high latency, or pull performance for the last 24 hours. For teams juggling multiple arrays, this turns routine health checks into a single conversation. Storage object lookup Query volumes by naming pattern, list file systems on FlashBlade, or inspect workloads on a specific array. Useful for anyone who inherited naming conventions from a previous geological era. Configuration audit Use the built-in documentation and read-only fetch coverage to compare settings across arrays and check for policy consistency. Handy if you’re trying to catch drift without hand-rolling an audit script every quarter. Workload lifecycle acceleration Enable supervised writes and the assistant can recommend placement, create or update presets, and deploy workloads from those presets. At that point the server stops acting like a reporting tool and starts acting like an interface layer for intent-driven operations. On My Soapbox: Why the Open Source release matters Being open source here changes the trust model, not just the distribution channel. You can inspect how the bridge works, check the security assumptions yourself, and contribute fixes instead of filing a ticket into the void. When reality disagrees with the documentation, which happens to every project sooner or later, you can open an issue instead of just living with it. The repository is public under Apache 2.0, with contribution guidance, architecture notes, a developer guide, and a dedicated issue tracker for support, issues, and feature requests. That means the people who’ll stress-test this in real environments can also be the ones fixing it. For a tool sitting between AI agents and production-adjacent storage workflows, that’s where the engineering conversation belongs. Final thought Fusion MCP Server is short on hype and long on mechanical sympathy. Read workflows stay front and center, write workflows require your explicit sign-off, and installation doesn’t eat your afternoon. If you’re running Fusion-managed fleets (which y’all should be!), it’s worth a look. Grab the latest release, point it at your MCP-capable agent, start read-only, and see how fast “show me my fleet overview” becomes second nature. It’s open source. Once you’ve kicked the tires, contribute code if you build something useful, and open an issue when you hit an edge case. That’s the whole deal.Purity Fusion Recipes
I have been loading up our fleet with a bunch of these predefined recipes and management have really enjoyed the information. I will say that most of these are very straight forward to setup but the Rubrik one was giving me troubles. I stumbled upon this link and it walked me everything perfectly. Almost all the recipes are listed here step by step and make this so easy. https://support.purestorage.com/bundle/m_pure1_manage_workflows/page/Pure1/Pure1_Manage/pure1_manage_workflows/topics/reference/recipe_template/protection/r_rubrik_cyber_resilience_visibility_template.html
Fusion preset: VMFS datastore volumes for VMware ESXi clusters (with two-tier snapshots and QoS)
Hi all, I put together a Fusion preset for one of the most common block use cases in our environment: provisioning VMFS datastore volumes for a VMware ESXi cluster. What it does: - 4x 4 TiB datastore volumes on a FlashArray//X storage class (adjust count/size to your cluster design) - Two-tier snapshot retention: hourly snapshots kept for 1 day (fast rollback) plus daily snapshots kept for 30 days - Per-volume QoS limit (50k IOPS / 1 GiB/s) so a single datastore cannot starve the array - An "environment" parameter (prod/test/dev) that is requested at deployment time and written into the workload tags for filtering and chargeback The JSON follows the conventions of the official PureStorage-OpenConnect/fusion-presets repository, including the _comment documentation style. One honest note is included in the preset itself: array-side snapshots of VMFS datastores are crash-consistent, not VM-consistent, so treat them as an extra safety net next to your backup solution. GitHub link: https://github.com/knabespecht/pure_workflows/blob/main/presets/vmware-esxi-datastores.json Feedback welcome, especially on the QoS defaults and retention values you use for similar setups.Ask Us Everything Recap: Rethinking Storage with the Intelligent Control Plane
The latest Ask Us Everything session focused on a topic that’s quickly becoming central to Everpure’s strategy: the intelligent control plane. And based on the questions from the community, it’s clear that many teams are starting to think beyond individual arrays and toward managing storage as a unified platform. Here are the key takeaways—driven by the questions attendees asked and the answers from Everpure experts Don Poorman, Zane Allyn and Mike Nelson. “Do I need to rebuild my automation to use Everpure Fusion?” Most teams already have automation in place, whether it’s Terraform, Ansible, or years of scripts. The good news: you don’t have to start over. Everpure Fusion is API-driven, so existing workflows can stay intact. In practice, you’re simply shifting from targeting individual arrays to targeting the fleet as a whole. That often means adding a parameter, not rewriting everything. Everpure Fusion picks up where any existing automation gets bogged down, so tasks get simpler as you scale, not more complex. The takeaway: Everpure Fusion helps you scale your existing automation—it simplifies, standardizes and extends it across your data estate. “What does API-first really mean here?” At Everpure, API-first isn’t just a label. The APIs are built before the GUI, which means everything you can do in the GUI is already available programmatically. For practitioners, that translates to flexibility. Whether you’re scripting, using infrastructure-as-code, or experimenting with AI-driven workflows, you’re not waiting for features to be exposed—you already have access. It’s a subtle difference from legacy storage, where automation often lags behind the interface. “How do I approach automation without losing control?” Attendees raised a common concern: automation can feel risky. The advice was straightforward—start with outcomes, not everything at once. Automate a single workflow, apply guardrails, and expand gradually. Automation here isn’t about removing control. It’s about: Reducing repetitive work Minimizing human error Freeing up time for higher-value tasks For most admins juggling multiple systems, that shift is practical—not theoretical. “What does this look like in real workflows?” One of the most relatable examples discussed was a ServiceNow-style request flow. Instead of manually provisioning storage across multiple systems, a user submits a request describing what they need—performance, protection, and resiliency. From there, Everpure Fusion and Pure1 handle the process automatically. The result is faster, more consistent delivery with fewer manual steps. More importantly, it abstracts the complexity away from both the admin and the requester. That’s a major difference from legacy environments, where admins must manage each step across each array. “What do I actually need to install?” This answer surprised some people. Everpure Fusion isn’t a separate product. It’s built into Purity. Once you’re on the right version (Purity//FA 6.8.1 or later, Purity//FB 4.5.5 or later), getting started is simple: Create a fleet Add arrays That’s it. No additional infrastructure, no separate control plane to deploy. This lowers the barrier significantly and makes it easy to start small and build as your needs require. “How does this scale?” As expected, scale came up quickly. Instead of managing arrays individually, Everpure Fusion introduces fleet-level management. New capabilities like topology groups allow further organization within that fleet—by region, workload, or compliance requirements. This is where Everpure’s approach really diverges from legacy storage. You’re no longer limited to thinking in terms of hardware. You can organize storage in ways that reflect how your business actually operates. “What happens if something fails?” Everpure Fusion is distributed across the arrays in the fleet. There’s no single point of failure. If one system goes offline, the rest of the fleet continues operating normally. That design keeps management resilient while still enabling centralized control. Final thoughts The biggest shift highlighted in this session is simple: Stop managing arrays. Start managing outcomes. With the intelligent control plane—powered by Everpure Fusion and Pure1—Everpure enables: Policy-driven automation Fleet-scale visibility Simpler, faster operations For storage teams, that means less time on manual tasks and more time focused on how data supports the business. And based on the conversation, that’s exactly where our customers want to go. Find out more about the Everpure Intelligent Control Plane here. Check out this and all our other Ask Us Everything sessions. And, keep the conversation going by jumping into the Everpure Community.
