The Present Context: Control Over Your Data
In our first post of a three-part AI series, we emphasized that control over your data is vital, especially in the current landscape of widespread AI deployment. The fundamental message was clear: You don't own your data if you can't control it, and you don't control your data if you can't roll it back.
Narrowing the focus to AI in data protection — specifically how AI is beginning to appear in backup and recovery — this blog explores Model Context Protocol (MCP) and what Keepit is building as an AI integration using MCP. The goal is to enable AI for backup and recovery while preserving control, data sovereignty, and resilience.
This second post in the series focuses on the practical "today and near-term" reality: what AI can reasonably do for backup and recovery now, and how MCP makes that possible without copying data into models you don't control.
Understanding Model Context Protocol (MCP)
Model Context Protocol (MCP) enables AI apps and agents to call approved external tools, resources, and prompts in a standardized, auditable way. Rather than copying enterprise data into a public model, MCP invokes tools to fetch facts (metadata, read-only) from systems you already control. Inputs and outputs can be logged, reviewed, and repeated.
In Keepit's implementation, AI queries the tools, the tools call Keepit's APIs, and answers come from immutable backups — no new data store required. This architecture ensures data sovereignty and control remain with the organization.
From AI Everywhere to AI for Backup and Recovery
Across organizations today, AI assists with writing, coding, analysis, and more. However, backup and recovery is a different domain with a tighter mandate: know what's protected, explain what changed, prove it with evidence, and restore the right data from the right point in time, no matter what — all while knowing where your data has been.
In this domain, AI's role is not to become a new data store. Instead, it interrogates systems of record you already control and presents answers and summaries quickly and consistently, in ways you can audit and repeat.
Three Tiers of AI Automation for Backup
To keep this grounded, consider three tiers of automation that build on one another, with each step bringing new capabilities as AI advances.
Tier 1: Human-Driven Inspection
AI helps people see and explain what's happening, but humans decide and make changes. Typical outcomes include:
- A current picture of protection status across services and tenants
- Audit summaries (who/what/when/why)
- Anomaly triage with likely causes
- Guided reasoning on what to restore, from when, and in what order
Keepit's AI integration (using MCP) exposes read-only capabilities across connectors and their health, jobs and snapshots, audit logs, and anomaly signals. Admins can query these against independent, immutable, always-hot backups.
Tier 2: Human-in-the-Loop Automation (HITL)
Think of the Iron Man suit: there's still a person inside, but the system amplifies what they can do. AI drafts compliance reports, assembles evidence packs, proposes restore plans with preflight checks, and recommends retention and hygiene actions at super speed — but all requiring explicit approval. Every step is logged, reversible, and bounded by policy.
This is where skills shine — plain-text workflows that standardize how jobs are analyzed, how quarterly audit reports are built (for example, GDPR mapping), and how account health is summarized, while the AI integration fetches facts from systems you control.
Tier 3: Fully Agentic Actions (The Future)
Agents act within tight boundaries: initiate restores, quarantine suspect areas, roll back to last-known-good across workloads — without a person in the loop. This tier demands rigorous guardrails (policy-as-code, approval gates, blast-radius limits, simulators and dry runs, full observability) and guaranteed reversibility grounded in immutable backups.
Across all tiers, the principle holds: Data stays in systems you control; answers and actions remain explainable and reversible.
The Technical Architecture
Keepit has utilized MCP as a way for AI apps and agents to call specific tools, helping businesses avoid the risks associated with copying enterprise data into a model where they can't control their data.
In Keepit's AI integration, MCP tools sit in front of Keepit's API surface — more than 200 endpoints across inventory, connector health, job history, snapshot ranges, audit logs, and anomaly signals. The integration gives AI clients a consistent way to use those APIs to interact with backup metadata.
The authoritative source of truth remains in independent, immutable backups. Organizations never give up control over their data; the AI client calls tools to fetch facts and present them in a read-only format. At a high level, a request flows like this:
AI client ↔ Keepit AI integration (MCP) ↔ Keepit APIs ↔ backup metadata
The client interprets a question, selects a tool, the tool hits the relevant API or APIs, and the result returns in a structured, explainable format.
Current Capabilities of Keepit's MCP-Based AI Integration
The initial surface is read-only by design, focusing on low-risk, high-value queries admins already ask:
- Reviewing connector posture and highlighting unhealthy states with likely root causes
- Inspecting jobs and snapshot ranges to explain recent failures
- Pulling scoped audit logs and assembling summaries suitable for governance stakeholders
Defined prompts available in the AI integration preview program include:
Estate overview and health:
- Totals and inventory: Count all connectors, list their GUIDs, and show each connector's current health
- Snapshot freshness: Highlight connectors with latest snapshot older than 24 hours
Audit and compliance: - Broad review: Pull prior 90 days of audit logs; summarize by action type, actor, and failures
Executive and periodic reports: - Quarterly compliance: Summarize protected connectors, worst snapshot staleness, job failure trend, and notable audit events
From Prompts to Procedures: Skills
Some MCP-aware clients now support "skills" — plain-text workflow descriptions that group and describe tasks for more complex operations than ad-hoc prompts. Keepit is drafting specific skills for job history analysis, compliance-audit logs, and account health.
Under the hood, a skill is a simple text file: a short overview, a handful of keywords, and then a detailed workflow that spells out time periods, frameworks, classification rules, and expected outputs.
When actions are eventually enabled (for example, restore workflows), they will be bounded, approved, auditable, and reversible. Until then, inspection and explanation have already delivered value without expanding the blast radius.
Maintaining the Control Theme
This approach operationalizes fundamental principles for AI in backup and recovery:
- Independence: Queries hit a vendor-neutral backup, outside production's blast radius
- Immutability: Results are grounded in tamper-proof history and point-in-time truth
- Rollback: Insights point directly to exactly what to restore and from which point in time
- Auditability: Tool calls, parameters, and outputs are loggable and reviewable
The outcome is straightforward: AI helps organizations move faster without giving up the ability to explain and reverse changes. The AI integration ensures organizations know where their data goes and has been stored, supporting digital and data sovereignty.
Looking Ahead
Keepit's AI integration provides a practical way to let AI participate in backup and recovery without moving data or giving up control. The company will expand tool coverage and skill library based on where admins and customer insight see the most value.
Any move into actions will retain the same discipline: guardrails, approvals, and easy rollback. The third and final blog in this AI series will explore what becomes possible next as AI matures in data protection — and how to pursue it without compromising control, independence, or the ability to roll back changes.
Sources
Keepit: AI of Tomorrow - What MCP Enables for SaaS Backup and Recovery Keepit: AI of Today - Control Over Your Data Keepit AI Preview Program