Governed Veeam Backup & Replication ops β 12 MCP tools with audit, budget, undo guards.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Disclaimer: Community-maintained open-source project. Not affiliated with, endorsed by, or sponsored by Veeam Software. "Veeam" is a trademark of its owner. MIT licensed.
AI-powered Veeam Backup & Replication operations with a built-in governance
harness β unified audit log, policy engine, token/runaway budget guard,
undo-token recording, and descriptive risk tiers. Self-contained: no
external dependencies beyond httpx and the MCP SDK. Coverage is not yet full
coverage of every Veeam operation.
Verification status: the test suite is mock-based; this package has not yet been validated against a live Veeam B&R server. See docs/VERIFICATION.md.
veeam-aiops ...): init, overview, job list/get/start/stop/retry/enable/disable, restore list-points/start, repository list/get/state, session list/get/log/stop, backup list/objects, diagnose job-failures/repo-capacity, infra servers/proxies, secret set/list/rm/migrate/rotate-password, doctor, mcp.veeam-aiops mcp or veeam-aiops-mcp): 25 tools (17 read, 8 write), every one wrapped with the bundled @governed_tool harness.diagnose job-failures triages recent job sessions β flags every Failed/Warning run and categorizes the likely cause (repository full, source/guest unreachable, credential/VSS failure, retry exhaustion), citing the session result + matched error substring; diagnose repo-capacity flags repositories under the free-space thresholds (<15% warn, <10% critical). Both cite the measured number that tripped each finding, worst-first.~/.veeam-aiops/secrets.enc (Fernet + scrypt) β never plaintext on disk. Unlock with a master password from VEEAM_AIOPS_MASTER_PASSWORD (MCP/CI) or an interactive prompt (CLI).high risk.session list / session get / session log (the runaway budget guard prevents poll loops from running away).It delivers Veeam Backup & Replication operations β reads and writes β accurately and efficiently, and records every one of them. It does not decide whether a write is allowed to happen. That is the agent's judgement, or the permission of the Veeam account you connect it with: give that account a read-only or restricted role on the VBR server and the writes fail at the server β the place that actually owns the permission.
So there is no read-only switch, no policy file, no approval gate to configure.
The one thing the tool guarantees is that nothing is silent: every call, over
MCP and over the CLI alike, lands an audit row in ~/.veeam-aiops/audit.db,
and reversible writes still capture their before-state and record an inverse.
Each tool declares a
risk_level, kept in agreement with its[READ]/[WRITE]documentation tag by a test, and carried into the audit row as a descriptive tier β so a reviewer can see at a glance that a row was a high-risk restore. It is a label, not a gate.
Running a smaller / local model? See agent-guardrails.md β it lists the guardrails this tool now enforces for you (so you don't spend prompt budget restating them) and gives a ready-made system prompt for what's left.
init writes ~/.veeam-aiops/config.yaml (non-secret connection details) and
stores the login password encrypted in ~/.veeam-aiops/secrets.enc. Example
config it produces:
For non-interactive use (MCP server, CI, cron) export the master password so the store can be unlocked without a prompt:
Migrating from an old ~/.veeam-aiops/.env (legacy VEEAM_<TARGET>_PASSWORD
vars)? Run veeam-aiops secret migrate; the old .env is renamed to
.env.migrated. The plaintext env var is still honoured as a fallback (with a
deprecation warning) for a smooth transition.
All operations are logged to a local SQLite audit DB under ~/.veeam-aiops/
(relocatable via VEEAM_AIOPS_HOME) β the harness records, it does not
authorize. Every call, over MCP and the CLI alike, lands an audit row; the
token/runaway budget guard is a safety backstop (not an authorization gate) that
stops a stuck agent from burning unbounded calls, and each row carries a
descriptive risk tier that gates nothing. Destructive CLI commands (job stop,
restore start) require double confirmation and support --dry-run.
API-returned text is run through a prompt-injection sanitizer.
Coverage is intentionally focused. Missing a device, action, or feature you need? Open an issue or pull request at github.com/AIops-tools/Veeam-AIops β feature requests, contributions, and comments are all welcome.
License: MIT.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/veeam-aiops)<a href="https://allmcps.com/mcp/veeam-aiops"><img src="https://allmcps.com/api/badge/veeam-aiops?style=directory" alt="Veeam AIops on AllMCPs" /></a>