Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Governed Veeam Backup & Replication ops — 27 MCP tools with audit, budget, undo guards.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"veeam-aiops": {
"command": "uvx",
"args": [
"veeam-aiops"
]
}
}
}Run this in your terminal
claude mcp add veeam-aiops -- uvx veeam-aiopsPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"veeam-aiops": {
"command": "uvx",
"args": [
"veeam-aiops"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"veeam-aiops": {
"type": "stdio",
"command": "uvx",
"args": [
"veeam-aiops"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account AIops-tools, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.20.0) reached the registry 8 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, MemberVault MCP by usefulapi
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
List courses; add users to courses, remove course access or delete users in MemberVault.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Audit availability: Real writes require a committed
pendingaudit row and stop before contacting the platform if storage is unavailable. Reads and previews may continue with a warning; new audit rows store outcome summaries rather than full responses.
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 — 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; selected CLI/REST reads
were validated against Veeam B&R 13.1.1.18. MCP lifecycle, writes, restore
safety, and later releases remain unverified on a live 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/usage/ranking, diagnose job-failures/repo-capacity, infra servers/proxies, secret set/list/rm/migrate/rotate-password, doctor, mcp.veeam-aiops mcp or veeam-aiops-mcp): 27 tools (19 read, 8 write), every one wrapped with the bundled @governed_tool harness.diagnose job-failures triages recent job sessions — 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) — 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 — reads and writes — 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 — 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 — 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 — 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.
One install gives an agent both the skill and the MCP server:
/plugin marketplace add AIops-tools/marketplace
/plugin install veeam-aiops@aiops-tools
The MCP server is fetched with uv and pinned to the package version this plugin declares, so an audit row can be traced back to the code that wrote it. Credentials are still configured with veeam-aiops init — see below.
The same bundle is published on ClawHub, where one install delivers the skill and its MCP server together:
openclaw plugins install clawhub:@zw008/veeam-aiops
openclaw skills info veeam-aiops # expect: Visible to model: yes
Restart the OpenClaw gateway afterwards so it loads the plugin. The MCP server is fetched with uv, pinned to this exact release, so uvx has to be on PATH — without it the skill still installs but reports Visible to model: no. Credentials are configured exactly as below.
uv tool install veeam-aiops
veeam-aiops init # interactive wizard: connection details + encrypted password veeam-aiops doctor # verify config, encrypted store, connectivity
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:
targets:
On a large VBR installation the
/jobsand/sessionsendpoints can take far
longer than the rest of the API — a live 13.1 environment did not answer a
single-record
/jobsquery inside 120 s while repositories answered in under
3 s.
timeoutlets you give those endpoints longer. It does not make a slow
endpoint fast: if a raised budget also expires, the endpoint is the
bottleneck, not this client. The same holds for
/backups/{id}/backupFiles,
which
backup rankingreads once per backup: a 123-backup 13.1 estate needed
timeout: 300for a complete ranking, and a backup that times out is flagged
(
timedOut) with this advice rather than silently left out. Scope the ranking
(
--backup,--repository) when you need part of the estate quickly.
For non-interactive use (MCP server, CI, cron) export the master password so the store can be unlocked without a prompt:
export VEEAM_AIOPS_MASTER_PASSWORD='your-master-password'
Where that password then lives: an exported variable is readable by
every process this shell starts and is recorded by shell history. On a
shared or long-lived host, prefer the interactive prompt, or inject it from
a secret manager for the life of the one command that needs it.
veeam-aiops secret set vbr-lab # prompts hidden for the password
veeam-aiops secret list # names only, values never shown veeam-aiops secret rm vbr-lab veeam-aiops secret rotate-password # re-encrypt under a new master password veeam-aiops secret migrate # import a legacy plaintext .env, then deletes it
Migrating from an old ~/.veeam-aiops/.env (legacy VEEAM_ _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) — 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 — feature requests, contributions, and comments are all welcome.
License: MIT.