mcpField
M
MSP360

MSP360

Local
github.comFiles & Storage0Updated 6d ago
RepositoryVisit website

About MSP360

MSP360 is an MCP server for managing and monitoring MSP360 Managed Backup Service accounts. It covers companies, computers, backup plans, monitoring, and licenses, with tools to start or stop backup runs.

Key features

  1. 01List and retrieve companies
  2. 02Browse managed computers
  3. 03Inspect plans and run history
  4. 04Start or stop backup runs
  5. 05Check monitoring and licenses

Use cases

  1. 01Review backup health across endpoints
  2. 02Check a plan’s run history
  3. 03Start or stop a backup run

MCP support

Exposes MSP360 Managed Backup Service API operations as MCP tools for AI assistants and the WYRE Conduit gateway. Supports stdio and HTTP transports.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "wyre-ai-msp360": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "MSP360_USERNAME",
        "-e",
        "MSP360_PASSWORD",
        "-e",
        "MCP_TRANSPORT",
        "-e",
        "AUTH_MODE",
        "-e",
        "LOG_LEVEL",
        "ghcr.io/wyre-ai/msp360-mcp:v1.0.1"
      ],
      "env": {
        "MSP360_USERNAME": "<MSP360_USERNAME>",
        "MSP360_PASSWORD": "<MSP360_PASSWORD>",
        "MCP_TRANSPORT": "<MCP_TRANSPORT>",
        "AUTH_MODE": "<AUTH_MODE>",
        "LOG_LEVEL": "<LOG_LEVEL>"
      }
    }
  }
}
Run commanddocker run -i --rm -e MSP360_USERNAME -e MSP360_PASSWORD -e MCP_TRANSPORT -e AUTH_MODE -e LOG_LEVEL ghcr.io/wyre-ai/msp360-mcp:v1.0.1
Environment variables to set
MSP360_USERNAMEMSP360 Managed Backup Service provider-portal username
MSP360_PASSWORDSecretMSP360 Managed Backup Service provider-portal password
MCP_TRANSPORTTransport mode for the server. Set to 'stdio' for local CLI use; the image defaults to 'http' for gateway hosting.
AUTH_MODESecretCredential source: 'env' reads vars locally, 'gateway' expects header injection from the WYRE MCP Gateway.
LOG_LEVELLog verbosity: debug, info, warn, error

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocighcr.io/wyre-ai/msp360-mcp:v1.0.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MSP360 MCP Server

MCP server for MSP360's Managed Backup Service API (formerly CloudBerry Lab) - companies, managed computers, backup plans, monitoring, and licenses, for AI assistants and the WYRE Conduit gateway.

Authentication

Provide the Managed Backup Service provider-portal UserName/Password pair. This server exchanges it for a short-lived bearer token via POST /api/Provider/Login and caches it, re-authenticating automatically whenever the vendor rejects the cached token (HTTP 401) - callers only ever need to supply the long-lived username/password.

Configuration

Env varDescription
MSP360_USERNAMEMSP360 provider-portal username.
MSP360_PASSWORDMSP360 provider-portal password.
MCP_TRANSPORTstdio (default) or http.
AUTH_MODEenv (default, reads the vars above) or gateway (credentials arrive per-request via X-MSP360-Username / X-MSP360-Password headers, injected by the Conduit gateway).
CONDUIT_S2S_SECRETWhen set, the HTTP transport requires a valid X-Gateway-S2S header (Conduit sidecar auth) on every /mcp request.
LOG_LEVELdebug | info (default) | warn | error.
Request limits
  • HTTP request bodies are capped at 256 KiB (262144 bytes). After the X-Gateway-S2S check passes, a Content-Length above the cap returns 413 with a JSON-RPC error; bodies without Content-Length are capped by the MCP SDK transport. Unauthenticated requests still get 401 first.
  • tools/call arguments are capped at 10,000 elements (every array item and object key at any depth). Larger inputs return an isError tool result and are never dispatched.

These limits address CVE-2026-111768 / GHSA-46jr-4wx8-v453 (memory exhaustion during validation) and GHSA-f897-62hf-6gxq (no request body / batch cap).

Tools

Companies
  • msp360_list_companies - list companies (customer organizations) under this provider account.
  • msp360_get_company - get a single company by ID.
Computers
  • msp360_list_computers - paginated list of managed computers (endpoints).
  • msp360_get_computer - get a single computer by HID.
Backup Plans
  • msp360_list_plans - list backup/restore plans on a computer.
  • msp360_get_plan - get a single plan by ID.
  • msp360_get_plan_info - get status/info for a plan.
  • msp360_get_plan_history - get run history for a plan, optionally filtered to a date.
  • msp360_start_plan - start a backup run for a plan.
  • msp360_stop_plan - stop a currently running backup for a plan.
Monitoring
  • msp360_get_monitoring - status data for the latest plan runs on all endpoints.
  • msp360_get_monitoring_for_user - status data for the latest plan runs, filtered by user.
Licenses
  • msp360_list_licenses - list available licenses, optionally filtered to unassigned ones.
  • msp360_get_license - get a single license by ID.

Scope

This is a v1 / MVP surface covering the core "what's backed up and is it healthy" MSP workflow. Explicitly out of scope for now: Administrators, Billing, Builds, Packages, Destinations/Accounts (storage-provisioning config), Users/Authenticate, and License Grant/Release/Revoke (mutating license assignment) and computer authorization/de-authorization - these are provider/reseller-admin-console-level operations with real billing/access consequences, distinct from day-to-day MSP monitoring, and worth a deliberate separate decision later rather than bundling into v1.

Development

npm install
npm run build
npm test
npm run lint   # tsc --noEmit

Docker

docker build -t msp360-mcp .
docker run -p 8080:8080 -e MSP360_USERNAME=... -e MSP360_PASSWORD=... msp360-mcp

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.