VSPC MCP server
Provides tools for interacting with the Veeam Service Provider Console (VSPC) REST API v3, giving cross-client visibility into companies, backup servers, Veeam Backup & Replication jobs, Veeam Agent jobs and Veeam Backup for Microsoft 365 jobs, including failed-job summaries with failure reasons, active alarms, protected VMs, backup policies, and license usage. Includes write tools to start or retry a job and acknowledge or resolve an alarm.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@VSPC MCP server which backups failed in the last 24 hours?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
VSPC MCP server
An MCP server for the Veeam Service Provider Console (VSPC) REST API v3. VSPC sees every client's Veeam Backup & Replication servers, Veeam Agents and Veeam Backup for Microsoft 365 servers, so Claude can answer questions across all clients in one call, for example "which backups failed in the last 24 hours?". Separately named write tools can start or retry a job and acknowledge or resolve an alarm.
It uses the same framework as Cititec's other MCP servers: TypeScript, @modelcontextprotocol/sdk, a stdio transport, vitest tests, tsup and a Docker image.
The API
VSPC 9.1 = REST API 3.6.1, at
https://<console>:1280/api/v3. Paths, filters and fields were taken from Veeam's OpenAPI document for 3.6.1 (the one the console serves on its Swagger page).Authentication: a Simple REST API key, sent as
Authorization: Bearer <key>on every request. No token exchange, and the key does not expire; it works until its user is disabled or deleted. Create it in VSPC under Configuration > Access Management > REST API Keys (scoperest). Tick read-only unless the write tools are wanted: a read-only key allows GET only.API contract: every request sends
X-Client-Version: 3.6.1, so a newer console answers in the 9.1 contract the tools were written for.Collections are paged with
limit(max 500) andoffset.meta.pagingInfogivestotal,countandoffset. Every list tool returnstotal,count,offsetandnextOffsetwhen there is more.Filters are JSON in the query string (
filter=[{"property":"status","operation":"equals","value":"Failed"}]). Tools build them from typed parameters. No tool takes a free-form path, filter or property name.No session history. VSPC v3 has no job-session endpoint. Each job carries its latest session: result, start, end and failure message. "Failed in the last N hours" therefore means "the latest session failed and ended in the last N hours". A job that failed and then succeeded on retry is not a failure any more.
vspc_failed_jobs_summaryadds VSPC's own session counts for the window (the job-session heatmap), which do include every session.
Related MCP server: Veeam AIops
Configuration
Variable | |
| The console address, https only, with its port: |
| The Simple REST API key. Never logged; removed from every error message. |
|
|
|
|
Tools
Read tools only send GET requests. Results are trimmed to the useful fields. Company and server UIDs are turned into names, and each response is capped at 60,000 characters. company accepts a company's UID or its name (an exact or unique partial match). A job belongs to one company: the company it is assigned to (mappedOrganizationUid), or the backup server's owner (organizationUid) when it is not assigned. A job on a hosted server shows under, and is filtered by, that one company. It is not listed for the provider that owns the server. A company name is resolved after reading every match (up to 1,000), so an exact match always wins. The organisation and backup server name lists are cached for 5 minutes per console and key (a failed lookup is not cached). Secrets in VSPC responses, such as a company's owner credentials, are never returned.
Tool | VSPC endpoint(s) |
|
|
|
|
|
|
|
|
|
|
| All three job lists, filtered on the latest result (Failed, optionally Warning) and paged through: every failure in the last N hours across all companies, newest first, with the failure reason |
| As above, one row per job. Retries of a job, and an agent job failing on several computers of one company, are folded together. Also gives counts per company and the session counts from |
|
|
|
|
|
|
|
|
|
|
Job sources in the failure tools:
backup_server: Veeam Backup & Replication jobs, including agent jobs managed by VBR.agent: Veeam Agents managed by VSPC.vb365: Veeam Backup for Microsoft 365 jobs.
If one source fails (for example, the key's user cannot see VB365), the others are still returned. The failed source is reported under scanned.
Write tools
Each write tool makes exactly one POST to a fixed endpoint, with a validated UID and no lookups first. On the Cititec MCP host, the proposal an administrator approves is exactly what is sent. Writes are never retried. They need a key that is not read-only.
Idempotency. VSPC treats X-Request-id as an idempotency key for 5 minutes. A write's id is derived from the tool name and its validated arguments (canonical JSON, keys sorted; SHA-256 shown as a version 8 UUID). If an identical write is sent again within 5 minutes, VSPC runs it once. Examples: a response lost on the network and sent again, or the same proposal approved twice. A different job, alarm or comment gets a different id. So does the same write more than 5 minutes later. Starting the same job twice on purpose within 5 minutes therefore runs it once. Reads send no request id.
Tool | VSPC endpoint |
|
|
|
|
|
|
|
|
Rate limits (Cititec fleet 429 policy)
VSPC throttles with HTTP 429 and gives the wait either in a Retry-After header or in a retryAfter property in the body.
Reads (GET): retried once if the wait is 10 s or less.
Longer or missing wait: the tool returns at once with a structured error:
structuredContent: { "error": "rate_limited", "retryAfterSeconds": N }, plus the textTry again in N s.Writes: never retried.
Running it
npm ci
npm run build
VSPC_URL=https://vspc.example.local:1280 VSPC_API_KEY=... node dist/index.js # stdio
npm testThe Docker image is ghcr.io/cititec-pty-ltd/vspc-mcp. It is published by the Cititec release workflow (semantic-release) on every release commit to main. On the Cititec MCP host, each connection gets its own container (docker run --rm -i) with the service's env file.
Licence
Available Tools
17 toolsvspc_aboutARead-onlyIdempotent
Veeam Service Provider Console version and installation details (server version, current Veeam Agent and management agent versions). A cheap first call to check the connection and key.
Inputs: no named parameters.
vspc_acknowledge_alarmA
Acknowledges a triggered VSPC alarm (alarm UID from vspc_list_alarms) with a comment. The alarm stays until it is resolved.
Inputs: comment (required), alarm_uid (required), on_client_portal.
vspc_failed_jobs_summaryARead-onlyIdempotent
Summary of backup failures across ALL companies in the last N hours: one row per job (retries of the same job, and one agent job failing on several computers of a company, are folded together, worst result first), counts per company, and VSPC's session counts (successful, warning, failed sessions) for the window. The best first call for "which backups failed in the last 24 hours?".
Inputs: hours, company, include_warnings.
vspc_get_companyARead-onlyIdempotent
One company: status, reseller, subscription plan, services enabled for it (owner credentials are never returned).
Inputs: company (required).
vspc_get_console_licenseBRead-onlyIdempotent
The VSPC console license: edition, package, status, expiry and support expiry, last update result.
Inputs: no named parameters.
vspc_get_license_usageARead-onlyIdempotent
Current license usage by organization and server (Veeam Backup & Replication, Cloud Connect, VB365, VSPC, Veeam ONE): per workload type the used, new and rental units and counts, plus totals per workload across the result. Optionally one company.
Inputs: limit, offset, company, server_type.
vspc_list_agent_jobsBRead-onlyIdempotent
Jobs of Veeam Agents (Windows, Linux, Mac) managed by VSPC, such as backup policies on workstations and servers: computer, company, policy, latest result, last run, next run, failure message.
Inputs: name, limit, offset, company, +1 more.
vspc_list_alarmsARead-onlyIdempotent
Triggered (active) VSPC alarms across every client, newest first: alarm name, status (Error, Warning, ...), time, message, the object (job, server, agent, repository...), computer and company. Defaults to Error and Warning alarms.
Inputs: hours, limit, offset, company, +1 more.
vspc_list_backup_policiesBRead-onlyIdempotent
Veeam Agent backup policies defined in VSPC: name, OS, mode, who created it, last change, and how many companies and agents use it.
Inputs: name, limit, offset.
vspc_list_backup_serversBRead-onlyIdempotent
Veeam Backup & Replication servers managed by VSPC, across every client: name, company, version (with patch), role, and status (Healthy, Warning, Inaccessible).
Inputs: name, limit, offset, company, +1 more.
vspc_list_companiesARead-onlyIdempotent
Companies (clients) managed in VSPC, sorted by name: UID, name, status. Use a UID or name from here as company in the other tools.
Inputs: name, limit, offset, status.
vspc_list_failed_jobsARead-onlyIdempotent
Every job across ALL companies whose latest session failed (or ended with a warning) in the last N hours, newest first, with company, backup server or computer, and the failure reason. Covers Veeam Backup & Replication server jobs, Veeam Agent jobs and Veeam Backup for Microsoft 365 jobs in one call. VSPC keeps only the latest session of each job, so a job that failed and then succeeded on retry is not listed. For one row per job with retries folded together, use vspc_failed_jobs_summary.
Inputs: hours, company, sources, max_rows, +2 more.
vspc_list_jobsARead-onlyIdempotent
Jobs on managed Veeam Backup & Replication servers (VM backup, replication, backup copy, tape, file share, agent jobs managed by VBR): latest result, last run and end, duration, destination, failure message. Filter by company, backup server, latest result and name. For "what failed recently" across all clients, use vspc_list_failed_jobs or vspc_failed_jobs_summary.
Inputs: name, limit, offset, company, +3 more.
vspc_list_protected_vmsARead-onlyIdempotent
Virtual machines protected by managed Veeam Backup & Replication servers: VM, company, backup server, restore points, latest restore point date, sizes, immutability. oldest_first: true puts the VMs with the oldest latest restore point first (stale backups).
Inputs: name, limit, offset, company, +1 more.
vspc_resolve_alarmA
Marks a triggered VSPC alarm as resolved, with a comment. If the cause is still there, VSPC triggers it again.
Inputs: comment (required), alarm_uid (required), on_client_portal.
vspc_retry_jobA
Retries a failed job on a managed Veeam Backup & Replication server (only the failed objects are processed again). VSPC queues the retry and returns at once.
Inputs: job_uid (required).
vspc_start_jobA
Starts a job on a managed Veeam Backup & Replication server now (job UID from vspc_list_jobs or vspc_list_failed_jobs). VSPC queues the start and returns at once; check the result later with vspc_list_jobs.
Inputs: job_uid (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 17 tools
Tools map cleanly to distinct resources (companies, backup servers, VBR jobs, agent jobs, alarms, licenses, protected VMs, policies), and the descriptions actively disambiguate the trickiest pairs (vspc_list_jobs vs vspc_list_failed_jobs vs vspc_failed_jobs_summary) with explicit "use X instead" guidance. The only residual overlap is between list_jobs/list_failed_jobs/failed_jobs_summary, which is an intentional layering but still requires the agent to read descriptions carefully.
Almost everything follows vspc_<verb>_<noun> in snake_case (list_companies, get_company, start_job, retry_job, resolve_alarm). Two deviations stand out: vspc_failed_jobs_summary uses a noun-only lead instead of a verb, and vspc_about is a bare verbless noun, breaking the otherwise predictable pattern.
17 tools is on the heavier side of the ideal band, but each maps to a real object in an enterprise backup console (companies, servers, jobs, agents, alarms, licensing, VMs, policies), so most earn their place. A couple of the read variants (console license vs license usage, failed jobs vs summary) could arguably be merged or made flag-based.
Read coverage is strong, and the action surface (start/retry job, acknowledge/resolve alarm) covers the core triage workflow. However, there is no stop/cancel job, no session-history or per-job detail tool, no repository/agent inventory, and no create/update for policies or companies, leaving obvious dead ends such as 'a job is stuck and I can't stop it.'
Maintenance
Related MCP Connectors
Scopable MSP API: clients, quotes, assessments, compliance, QBRs. OAuth 2.1, read-only or read-write
List clients, devices, vaults and restore points, and check backup jobs in Axcient.
Linux server administration over OAuth MCP: shell, Docker, systemd, files and monitoring.
Read-only access to your SKRIME account: servers, domains, DNS, webspace and more via API key.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceExtends Veeam Intelligence to MCP-compatible clients, enabling secure, real-time operational insight across Veeam Backup & Replication, Veeam ONE, and VSPC via natural language or AI workflows.22MIT
- AlicenseAqualityAmaintenanceAI-powered Veeam Backup & Replication operations MCP server with tools for managing jobs, restores, sessions, and repositories, featuring built-in governance, audit logging, and safety controls.27MIT
- FlicenseNot gradedqualityCmaintenanceMCP server that exposes the Cove Data Protection (N-able Backup) Management Service JSON-RPC API as 247 tools for managing backup, recovery, and partner/account operations.-
- AlicenseAqualityDmaintenanceRead-only MCP server for the Action1 RMM REST API, enabling access to endpoints, missing updates, vulnerabilities, installed software, policies, automations, and reports.21Apache 2.0