Your management console holds everything about your deployment: every agent, job, run, and transfer. But getting answers from it has traditionally meant navigating the UI, decoding lengthy knowledge base articles, or sifting through lengthy API responses. Turning that raw activity into operational intelligence—the answers that keep a large deployment healthy—has always meant manual work.
The Resilio MCP Server, now in Early Preview, removes that work. You connect your management console to an AI client, ask a question in plain English, and get an answer based on your actual environment: real agent names, real run data, real error codes. It’s an early look at one of the themes anchoring the next big Resilio release—AI-powered operational intelligence—where running a large deployment becomes a conversation rather than a chore.
Here’s how it works. MCP (Model Context Protocol) is an open standard for connecting AI clients to external systems. When you connect the Resilio MCP Server to your AI client, the client is handed a list of 135 tools, and based on your question, it chooses the appropriate ones, much like an AI client normally chooses between searching the web or creating a file. These tools make API calls to your management console, but they aren’t just a wrapper over the API. Each tool comes with detailed instructions and contextual information about the management console, and the MCP includes a system prompt we’ve written that equips the AI to use them competently. You don’t need to configure any of this; it’s automatically adopted when the connection is established.
The MCP server is also connected to the Resilio Help Center knowledge base documentation. It has tools for searching and reading our knowledge base directly, so how-to, configuration, and troubleshooting advice comes from our documentation rather than from the internet.
What Can You Do With It?
In practice, the MCP acts as a knowledgeable troubleshooting, configuration-advising, and security-monitoring assistant for your management console. Some of the things you can do:
- Troubleshoot. Ask “Which jobs are failing right now?” and the MCP will find the failing runs, identify the agents involved, pull the specific error codes, and look up their meanings in the documentation. There are dedicated diagnostic tools for failing runs, offline agents, and stalled transfers.
- Ask configuration and how-to questions. Because the MCP can read both your console’s configuration and the official documentation, it can answer questions about your setup and advise on changes before you make them.
- Build custom reports. If you currently use the API for custom reporting, the MCP gives you a faster path to the same result. Ask a question in natural language and get a detailed report or visualization back, without writing or chaining API calls yourself.
- See change over time, not just the current state. Most of what we’ve described so far is about what’s happening in your console right now. With the Events database, coming soon in a future Resilio release, the MCP will also be able to query analytics, a time series record of agent actions, user changes, warnings, and errors. That lets you ask questions like “Which agents haven’t moved any data in the last 5 days, and why?” or “Which users or agents drove the most file changes recently, versus their baseline?” Most MCP tools work without 6.0, but you’ll miss out on these analytical tools.
- Monitor security. The Events database will also include an audit log, and the MCP can scan it for suspicious activity, repeated failed logins, privilege changes, abnormal spikes in file deletions, and other warning signs. You can ask “Run a security scan of my management console” or something as specific as “Flag any agent with an abnormal spike in file deletions in the last 24 hours.”
Safety and Security
We put a lot of thought into the safety of this MCP.
- It’s read-only by default. Out of the box, every tool the AI gets is a read: querying agents, jobs, runs, settings, and analytics. Write tools (creating jobs, modifying agents, and so on) are disabled unless you explicitly change the configuration to enable them.
- It runs locally. The MCP runs on your machine and communicates with your management console via the same token-authenticated REST API you already use. None of your data or credentials leaves your machine, apart from what you send to the AI client you’ve chosen to connect. Secrets are also automatically redacted from the MCP’s own logs.
- You control the permissions. The MCP authenticates to the console with an API token that you create, so the AI can only do what that token allows. We recommend creating a dedicated token scoped to just the permissions you want the AI to have, rather than reusing an admin token.
- Writes come with a safety net. If you do enable write tools, every write automatically creates a management console configuration backup before making its change, and if the backup can’t be created, the write is aborted. Keep in mind that a backup will not undo any files that have already been moved; it is just a snapshot of the configuration. So, double-check any changes before approving them.
Getting Started
Getting started is simple for Resilio customers with an existing API license. Install the MCP server, point it to your management console URL, add your API token, and connect it to an AI client such as Anthropic’s Claude Desktop, Claude Code, Cursor, or other MCP-compatible clients. Setup instructions are in the documentation, and you can download the MCP server to get started!
If you’re a current Resilio Active Everywhere customer, not yet using our API, contact your account manager to learn about adding an API license to your configuration.
Best Practices for Using Large Language Model (LLMs) with the Resilio MCP Server
Prerequisites
- The MCP server is installed and connected to your AI client (setup page)
- Resilio Management Console version 3.6 or later. Having 3.6 or later allows you to run most MCP tools already!
- For analytics and security scans, a future release of Resilio will enable these features. These tools are enabled automatically when the server detects a supported console.
- A dedicated, scoped Resilio API token for the MCP server. See Security recommendations below.
Important note: After changing your config file and saving it, you must quit and restart the AI client for the changes to take effect.
Start by asking questions
The fastest way to learn what the MCP can do is to ask it directly. A good first prompt:
‘List all the tools you have access to and suggest some questions I can ask’
From there, here are questions that show off what the MCP does well.
Troubleshooting. There are dedicated diagnostic tools for failing runs, offline agents, and stalled transfers.
- “Which jobs are failing right now, and why?”
- “Are all of my agents online? Investigate any that aren’t.”
- “Is anything stuck? Check for stalled transfers.”
- “Agent XYZ has a warning. Investigate its health and tell me what to do.”
Configuration and how-to. The MCP can read both your console’s configuration and the official documentation.
- “Give me a health overview of all my jobs.”
- “Explain what my X job is configured to do, and whether anything about it looks unusual.”
- “How do I set up a bandwidth schedule? Use the Resilio documentation.”
- “I want to add a new agent at a new site. Walk me through it and tell me what to decide in advance.”
Custom reporting. Anything you previously built by chaining API calls, you can now ask for in a sentence.
- “Build me a report of transfer volume by job over the last month, with a chart.”
- “Which five agents transferred the most data this week?”
Analytics. With the Events database coming in a future release of the Management Console, the MCP can query a time series record of agent actions, user changes, warnings, and errors. This lets you ask about change over time, not just the current state. Note: only analytics and security monitoring require this future release; every other MCP tool can run on 3.6 or later!
- “Which agents haven’t moved any data in the last 5 days, and why?”
- “Which users or agents drove the most file changes recently, versus their baseline?”
- “Show me error trends over the last two weeks. Is anything getting worse?”
Security monitoring. The Events database includes an audit log, and the MCP can scan it for suspicious activity (also requires the future release).
- “Run a security scan of my management console.”
- “Flag any agent with an abnormal spike in file deletions in the last 24 hours.”
- “Summarize login activity for the past week and point out anything unusual.”
Filing a support ticket
You can ask a question like:
‘Can you file a support ticket for me? I have an error that I can’t fix in my management console.’
The AI client will collect the necessary information and submit the ticket through the API.
Ask Your Management Console Anything
Investigating an Agent Warning
In this example, we will investigate a problem agent.
The AI pulls the job health overview and the full agent fleet, separates agents that are merely offline from agents with real errors, and summarizes the failing jobs:
From here, pick one error and go deeper:
What is the SE_BIND_PORT_BUSY error? How do I fix it?
The AI searched the Resilio documentation, found the page for this exact error, and returned the likely cause (two agents fighting over the same port on one host), the affected agent, and concrete commands to confirm and fix it.
Doing the same by hand means paging through the agents’ list, cross-referencing errors against jobs, and searching the docs yourself.
Setting up a Project
The AI can see your console through the MCP’s tools, but it does not know which jobs are critical, which agents run on slow links, or what your team’s rules are. A project is how you tell it once, not in every chat.
In Claude, a Project holds two things, and every conversation inside it inherits both:
- Instructions define behavior: what the AI should know about your environment and how it should act. Keep them short and factual.
- Knowledge files provide information the AI can consult when it needs to: escalation procedures, naming conventions, and site topology. If you would otherwise paste a document into the chat repeatedly, it belongs here.
Other AI clients have equivalents, and the concept is the same everywhere.
Writing Instructions that Describe Your Environment
Good instructions are mostly context that the AI can’t get from the tools, plus a few rules about behavior. A dozen lines are enough to start.
Add the context that the tools can’t surface. Don’t restate what the AI can discover on its own. It can already list your agents, jobs, and groups through the MCP, so writing “we have 40 agents across 12 sites” adds nothing. What the tools cannot tell is what any of that means: which jobs matter, what’s normal for your environment, and what counts as a problem. That’s what the instructions are for. For example:
This Management Console manages file delivery for ⟦TODO: one sentence on what the deployment is for, e.g., “our retail chain: nightly price and media updates from HQ out to store servers”⟧. The ⟦job name⟧ job is business-critical; treat any error on it as urgent. Agents matching ⟦prefix⟧-* sit on links under ⟦N⟧ Mbps, so slow transfers there are normal, not a problem. Our maintenance window is ⟦day/time⟧; offline agents during that window are expected.
Notice everything in that example is a judgment or a caveat, not an inventory. Good candidates: which jobs or agents are critical, known-slow or flaky links, expected downtime windows, naming conventions the AI should read meaning into, and anything your team has learned the hard way about this deployment.
Set the rules of engagement. Tell the AI how you want it to operate, for example, if you plan on enabling write tools:
‘Always confirm with me before running anything that changes the configuration. When answering how-to questions, search the Resilio documentation rather than answering from general knowledge, and tell me which article you used. If you can’t find something, say so instead of guessing.’
Help it use the tools well. Two lines we recommend adding:
Some AI clients send empty strings for optional parameters, causing tool calls to fail.
‘When calling tools, omit optional parameters you don’t need. Never pass an empty string. You can pass null’
For questions about what is configured right now, use the standard read tools. Use analytics only for questions about what happened over time.
The analytics database is an event history, not a snapshot of the current state. “How many jobs do we have?” should come from the read tools; “how many jobs were created this month?” is an analytics question.
Iterate. When the AI does something you did not want it to, add a line to the instructions. Projects improve one correction at a time.
Use AI to improve instructions. Ask the AI to suggest improved instructions based on your conversations.
One last recommendation, echoing the launch post: keep the MCP read-only while you build up your project, and use a dedicated API token scoped to just the permissions you want the AI to have. If you plan to change the configuration to allow for mutating changes, be sure to give the AI client the necessary information and double-check its work.
Setting up / Changing your configuration
As mentioned earlier, instructions for setting up the MCP are available here. One of these steps involves editing the MCP config file to include your credentials. But what if you want to change the config? Say you want to change your API token, configure the MCP to be able to make mutating changes to your management console, or run the MCP through HTTP rather than STDIO. You can always make configuration changes.
When to Use the MCP vs. the API Directly
The MCP server uses the same Management Console API you may already script against. The difference is who writes the call sequences. With the API, you chain calls and parse responses yourself. With the MCP, you describe the outcome, and the AI selects, sequences, and interprets the calls, and layers on things that would take time to build by hand, like documentation search, analytics SQL, and multi-step diagnostics.
When is the API better?
- Getting comprehensive enumeration lists without risk of AI omitting anything
- Sensitive write operations where you don’t want AI as your middleman
- The MCP exposes a curated subset of API calls; anything we left out for security isn’t reachable through the MCP. Those calls remain available through the API directly for users whose token grants the permission.
- Cases where you need a predictable workflow and deterministic results
- Third-party event-driven automation — using the API to trigger Management Console actions in response to external events.
Common Pitfalls
Empty strings in tool parameters
Some AI clients send an empty string (“”) for optional parameters the model didn’t fill in, instead of leaving them out. The server can’t convert an empty string into a number or a boolean, so the call fails before it runs. If you see unexplained tool call failures, especially on tools with numeric or boolean filters, add the “omit optional parameters” instruction from the previous section. The server’s built-in guidance already asks for this, but repeating it in your own instructions helps.
Support ticket confusion
You can file support tickets using the MCP in any mode. When you file through the MCP, the ticket is sent through the API. Occasionally, the AI client may suggest that you “send an email” to support, but this is no longer supported by Resilio as a way to file a ticket. If you don’t want to use the MCP or API to submit a ticket, you can also do so through the Management Console.
Enumeration requests
Requests for a comprehensive list—every agent, all jobs, etc.—become unreliable as the number of entries grows. The client may not page through the entire result set, and even when all data is present, the model can skip or drop individual entries as it works through a long list. The output often looks complete while silently omitting records. It is best to double-check such answers and understand that AI can silently miss entries, even when the data returned by the MCP is complete.
Security Recommendations
- Keep the MCP read-only while you build up your project. Write tools are disabled by default. Leave them off until your instructions are settled and you trust the answers you’re getting.
- Use a dedicated API token scoped to just the permissions you want the AI to have. Don’t reuse an admin token. Even with write tools enabled, a scoped token is a defense-in-depth measure: the AI can only do what the token permits.
- If you enable write tools, give the AI client the necessary context in your project instructions (including the confirm-before-changes rule above) and double-check its work.
Get Started with the Early Preview
The Resilio MCP Server is available today as an Early Preview. The best way to get started is to reach out to your account manager. They can help you add an API license if you don’t have one yet, connect the MCP Server to your management console, and get your team set up to put AI-powered operational intelligence to work ahead of the next Resilio release. Already have an API license? You can install the MCP Server straight from the documentation and start asking your console questions right now.
