acronis-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AUTH_MODE | No | Auth mode: `gateway` (Docker image and Compose default) or `env`. In `env` mode, `ACRONIS_*` are used only after S2S auth succeeds. | |
| LOG_LEVEL | No | Log level: `debug`, `info` (default), `warn`, or `error`. | info |
| MCP_HTTP_HOST | No | Bind address when a real `CONDUIT_S2S_SECRET` is set. Defaults to `127.0.0.1`; container image sets `0.0.0.0`. | 127.0.0.1 |
| MCP_HTTP_PORT | No | HTTP port. Defaults to `8080`. | 8080 |
| MCP_TRANSPORT | No | Transport: `stdio` (default) or `http`. | stdio |
| ACRONIS_BASE_URL | Yes | Acronis datacenter URL (https only, hostname must end with .acronis.com, no userinfo, no non-default port, no path/query/fragment). | |
| ACRONIS_POOL_MAX | No | Max concurrent upstream children (LRU). Default `50`. | 50 |
| ACRONIS_CLIENT_ID | Yes | Acronis API client ID. | |
| CONDUIT_S2S_SECRET | No | Service-to-service secret required for HTTP. Must be non-empty and not a known placeholder. Generate with `openssl rand -hex 32`. | |
| ACRONIS_POOL_IDLE_MS | No | Idle time in milliseconds before a child is closed. Default `600000` (10 min). | 600000 |
| ACRONIS_CLIENT_SECRET | Yes | Acronis API client secret. | |
| ACRONIS_ENABLE_WRITES | No | Set to `true` to expose the 3 write tools. Default `false`. | false |
| MCP_ALLOW_INSECURE_DEV | No | Set to `1` only for local development to start HTTP without `CONDUIT_S2S_SECRET`. Binds `127.0.0.1` only and does not enforce `X-Gateway-S2S`. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| acronis_fetch_tenantC | Fetches a tenant by ID. |
| acronis_fetch_tenants_batchB | Gets several tenants at once, by up to 100 tenant IDs, by parent tenant, or as a tenant and everything under it. |
| acronis_fetch_tenant_childrenA | Lists the IDs of the tenants directly under a tenant, such as a partner's customers. |
| acronis_fetch_tenant_usersB | Fetches a list of UUIDs of the tenant's users. |
| acronis_fetch_users_batchC | Gets details for several users at once. |
| acronis_fetch_userC | Fetches a user by ID. |
| acronis_fetch_current_user_infoB | Fetches information about the currently authenticated user. |
| acronis_searchC | Searches for tenants and users. |
| acronis_fetch_tenant_mfa_statusC | Provides MFA status for tenant and progress of TOTP enablement by users. |
| acronis_fetch_tenant_usagesC | Fetches a list of common usage metrics of the tenant. |
| acronis_fetch_all_alertsC | Fetches all alerts by optional filtering parameters. |
| acronis_fetch_alertB | Fetches the information about the alert by ID. |
| acronis_fetch_categoriesC | Lists the alert categories that are turned on. |
| acronis_fetch_alert_countersC | Fetches the alert counters that may be grouped by optional parameters. |
| acronis_fetch_alerts_grouped_by_scopeB | Gets the most recent of the most severe alerts for each group, grouped by the scope you choose. |
| acronis_fetch_all_alert_typesC | Fetches all registered alert types. |
| acronis_fetch_resources_with_top_severity_alertsC | Fetches the resources' statuses that contain the alerts with the highest severity found for the resources. |
| acronis_fetch_alert_counts_per_customerC | Fetches count of alerts per customer. |
| acronis_fetch_alerts_grouped_per_customerC | Fetches alerts of the specified customers. |
| acronis_fetch_active_alert_countB | Returns count of active alerts and last modification time. |
| acronis_fetch_policiesC | Lists protection policies (called protection plans in the Acronis console). |
| acronis_fetch_policyB | Gets one protection policy and its settings by ID. |
| acronis_fetch_policy_applicationsC | Lists where policies are applied, meaning which resources each policy covers, with optional filters. |
| acronis_fetch_applications_issue_statisticsC | Counts problems with applied policies, grouped by issue. |
| acronis_fetch_application_statuses_by_policyC | Gets the status of every resource a given policy is applied to. |
| acronis_fetch_resourcesC | Lists resources (machines, mailboxes and other workloads), with optional filters. |
| acronis_fetch_resource_countC | Fetch a count of all resources that match filter parameters. |
| acronis_fetch_resourceC | Gets one resource (a machine, mailbox or other workload) by ID. |
| acronis_fetch_resource_protection_statusC | Shows which resources are protected and which aren't. |
| acronis_fetch_agentsC | Lists the Acronis agents installed on machines in a tenant. |
| acronis_fetch_agentB | Gets one Acronis agent by ID. |
| acronis_fetch_incidentsC | Lists EDR security incidents, with optional filters. |
| acronis_fetch_incidentB | Gets the details of one EDR security incident by ID. |
| acronis_fetch_response_action_statusB | Gets the status of a response action that was started on an incident, such as isolating a machine. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 34 tools
The tenant, user, policy, resource, agent, and incident tools are mostly distinguishable. However, the alert surface has many overlapping-sounding tools such as fetch_all_alerts, fetch_alert_counters, fetch_alerts_grouped_by_scope, fetch_alerts_grouped_per_customer, fetch_alert_counts_per_customer, and fetch_active_alert_count, so selecting the right one requires careful reading.
Nearly all tools use a consistent acronis_ prefix followed by snake_case fetch_* names, with one search_ exception. Minor variations like fetch_alert vs fetch_all_alerts and grouped/count naming are readable and predictable.
At 34 tools, the surface is large for a single MCP server and is especially heavy in alert-related read variants. Several alert count/grouping tools could likely be consolidated without losing capability.
The server provides broad read-only coverage across tenants, users, alerts, policies, resources, agents, and incidents. However, it lacks lifecycle or mutation operations such as creating/updating policies, acknowledging or resolving alerts, or starting response actions, and fetch_response_action_status has no corresponding action-start tool.