Datto BCDR MCP Server
Provides read-only access to the Datto BCDR partner REST API for SIRIS and ALTO backup appliances, enabling AI agents to inspect appliances, protected machines and shares, snapshot and verification history, latest screenshot verification images, offsite replication status, fleet alerts, and partner portal activity logs.
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., "@Datto BCDR MCP Servershow me Datto alerts and failed snapshot verifications from this week"
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.
Datto BCDR MCP Server
An MCP server for the BCDR part of the Datto partner REST API (SIRIS and ALTO backup appliances). It lets an AI agent read appliances, the machines and shares they protect, snapshot history with local and screenshot verification, the latest verification screenshot, offsite (cloud) replication, alerts across the fleet and the partner portal activity log. It is read-only.
Transport: MCP Streamable HTTP at
POST /mcp, health probe atGET /healthStateless and multi-tenant: the key pair arrives on every request as HTTP headers and is never stored; every tool is listed from the first
tools/listPython 3.12, uv, FastMCP, httpx
License: Apache-2.0, Copyright 2026 MSPbots.ai
MSPbots Connector
The MCP Gateway built for MSPs: visible, controlled, and your data stays where it belongs.
Get started at connect.mspbots.ai →
MSPbots Connector gives your AI clients one MCP URL to reach your entire MSP stack (RMM, PSA, documentation, security, finance), and gives you control over who can call which tool and a record of everything that was called.
Hosted service: connect.mspbots.ai · Free to use.
Why Connector

Visible | Every tool call is logged: who, which vendor, when. Usage dashboard, CSV export, SIEM streaming. |
Controlled | Role-based, per-tool allowlist. Deny by default. |
Protected | Credentials encrypted per record. AI clients never see your vendor passwords or tokens. |
MSP-native | Built for the MSP stack only: RMM, PSA, documentation, security, finance. |
Quick start
Sign up at connect.mspbots.ai.
Connect your vendors. Pick from 150+ connectors and authorize each one on the vendor's own page, or bring your own API keys. No extra vendor accounts needed.
Set access. Create roles and decide which tools each role may call. Nothing is allowed until you allow it.
Add your MCP URL to your AI client. Copy the URL from your Connector dashboard into Claude, ChatGPT, Cursor, VS Code, Gemini, Codex, or any MCP-capable client.
Ask your AI to do real work, and watch every call appear in the audit log.
Features
Unified gateway
One MCP URL for all your AI clients
150+ connectors across the MSP stack
Custom MCP servers supported, free
Authorization happens on each vendor's own page; the AI never sees passwords or tokens
Bring your own credentials: use the vendor API keys you already have
Multiple accounts per app; connect once, reuse across AI clients
Tool search: finds the right action for the task
One sign-in; vendor credentials are injected behind the scenes and OAuth tokens refresh automatically
Visibility
Audit log for every tool call (who, which vendor, when)
Usage dashboard: call volume, top vendors, error rate, per-user activity
Export audit logs to CSV, or stream to Loki, Graylog, or LogScale (SIEM)
Optional recording of tool arguments and result summaries (off by default, enabled per organization)
Control
Per-role, per-tool allowlist, deny by default
owner / admin / member roles
SCIM provisioning with Entra ID, Okta, JumpCloud, and Google Workspace
Security
Credentials encrypted one record at a time (AES-256-GCM, per-record key)
AI clients authenticate with OAuth 2.1 + PKCE
Vendor responses are scanned for prompt-injection patterns and returned as structured data. This is one layer of defense, not a guarantee against every attack.
Static egress IP for customer firewall and API allowlisting
Pricing
Free.
Links: connect.mspbots.ai · mspbots.ai
Related MCP server: Auvik MCP Server
Authentication headers
Header | Required | Type | Default | Allowed values | Description | Example |
| Yes | string | none | - | Datto partner portal REST API public key |
|
| Yes | string | none | - | The secret key paired with it |
|
Where to get them: in the Datto partner portal open Admin -> Integrations, choose the REST API option and create an API key; the portal shows the public key and the secret key.
How the keys are sent to Datto: every call is a GET to https://api.datto.com/v1/... with
HTTP Basic authentication (public key as user name, secret key as password).
A request to /mcp without both headers gets HTTP 401 naming the missing one.
Tools
All tools return JSON except datto_bcdr_get_screenshot, which returns an image (Datto serves
it as JPEG). Appliances
are addressed by serialNumber; the agentId of the asset tools is the asset's volume name
(the name / volume field from datto_bcdr_list_assets). Datto timestamps are Unix seconds;
the tools add ISO 8601 ...At fields next to them.
The list tools with page / perPage also take offset (record position, overrides page) and
return offset / next_offset: a page cut to fit the response size limit has no other page holding
its rest, so next_offset starts right after the last record returned; pass it as offset to
continue without gaps.
Tool | Purpose | Parameters (required in bold) |
| Appliances: serial, name, model, client, last seen, storage, agent / alert counts | page, perPage (max 250), offset |
| One appliance with its agents, shares and current alerts | serialNumber |
| Machines and shares an appliance protects, with last snapshot, offsite and screenshot state | serialNumber |
| One protected asset: OS, agent version, volumes, paused / archived, last snapshot, offsite | serialNumber, agentId |
| An asset's snapshots, newest first: backup status, errors, local and screenshot verification | serialNumber, agentId |
| Screenshot (boot) verification: the latest attempt ( | serialNumber, agentId |
| The latest screenshot-verification image (JPEG) | serialNumber, agentId, epoch |
| Offsite storage used and each asset's latest offsite point; lists assets never sent offsite | serialNumber |
| Alerts currently open on all appliances, raised in a window (default last 7 days), newest first; cleared alerts are not returned (no history) | since, until, page, perPage, offset |
| Partner portal activity log (who did what, on which target), default last 7 days, at most the last 31 days | since, until, page, perPage, offset, clientName |
Errors come back as a JSON envelope instead of an exception:
{"error": {"code": "unauthorized", "message": "Datto returned HTTP 401 for bcdr/device", "retryable": false}}code is one of not_configured, unauthorized, not_found, invalid_argument,
rate_limited, upstream_error. Every call is a read, so 429, 5xx and network errors are
retried with backoff (honouring Retry-After). Datto's documented limit is 10,000 requests per
hour per organization.
Run locally
uv sync
uv run python -m datto_bcdr_mcp # listens on 0.0.0.0:8080or with Docker:
docker build --platform linux/amd64 -t datto-bcdr-mcp:dev .
docker run --rm -p 8080:8080 datto-bcdr-mcp:devConfiguration (environment variables, all optional): MCP_HTTP_HOST (default 0.0.0.0),
MCP_HTTP_PORT (default 8080), LOG_LEVEL (default INFO). The keys are never read from
the environment.
Testing example
# list tools
curl -s http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-H "X-Datto-BCDR-Public-Key: your-public-key" \
-H "X-Datto-BCDR-Private-Key: your-private-key" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
# snapshots of one protected server
curl -s http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-H "X-Datto-BCDR-Public-Key: your-public-key" \
-H "X-Datto-BCDR-Private-Key: your-private-key" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"datto_bcdr_list_backups","arguments":{"serialNumber":"your-serial","agentId":"SRV01"}}}'Unit tests (no network access needed):
uv run pytestDelivery notes
Tool count (10). Kept as is because the tool names are an existing contract.
Built on the documented endpoints. Older versions called routes that are not in Datto's API contract (
.../asset/{id}/backup,.../screenshot,.../screenshot/{epoch},.../offsite). This version uses only documented routes: snapshots and screenshot results come from the asset record'sbackups, the image from.../screenshot/latest, offsite state from the device and asset records.datto_bcdr_get_screenshot. The API serves only the latest screenshot, soepochis now optional; when given, it must match the latest screenshot's time or the tool says which time is available.No interactive prompts. Older versions asked the user for a serial number or date window mid-call, which a stateless gateway cannot relay.
datto_bcdr_list_assetsnow requiresserialNumber, and the alert / activity tools default to the last 7 days.Activity log. Datto keeps 31 days of activity (
sincemust be under 744 hours); an oldersinceis moved to 31 days ago and the result sayssince_clamped. Datto'sclientNameparameter returns no rows even for an exact name, soclientNameis matched here (case-insensitive, contains) over up to 1,000 entries of the window, then paged.Screenshot history. The API has no screenshot history: per-snapshot results come from the recent snapshots in the asset record (about the last 10), so
datto_bcdr_list_screenshotsreturns the latest attempt aslatestand says so when the per-snapshot list is empty.Fleet alerts.
datto_bcdr_list_alertsreturns the alerts currently open (Datto has no alert history). It reads the alerts of every appliance whose alert count is not zero (up to 1,000 appliances, 5 at a time) and pages the combined result.
License
This server cannot be deployed
Maintenance
Related MCP Connectors
- HAVNOAuthapp.havnre
Read-only AI access to HAVN properties, leads, tasks, files, media, and analytics.
Read-only access to an ET Ducky organization's agents, alerts, and fleet summary
Read-only access to your VortexIQ store data: audits, KPIs, alerts, Brand DNA, reports, Ask VIQ.
- ScopableOAuthio.scopable
Scopable MSP API: clients, quotes, assessments, compliance, QBRs. OAuth 2.1, read-only or read-write
Related MCP Servers
- AlicenseBqualityAmaintenanceEnables read-only visibility into Slide backup/BDR resources—accounts, agents, devices, networks, backups, snapshots, and restores—for AI assistants, while excluding secret-bearing fields and mutating operations.43Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to query an MSP's network monitoring data — tenants, discovered devices, networks, interfaces, configuration backups, alerts, performance statistics and billing usage — through multi-tenant, stateless Streamable HTTP with credentials supplied per request. Read-only by default, with optional alert dismissal and raw API access for changes.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to read-only query an MSP's Action1 data — organizations, managed endpoints, missing OS and third-party updates, and scheduled automations — using per-request credentials that are never stored. Supports multi-tenant, stateless access over Streamable HTTP with paginated list results and structured error responses.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to read protected customers and their backup health, seats, and per-application backup history, and on explicit request to license, pause, or unlicense seats.Apache 2.0