agentgates.aiVerified
Confidential computers for AI swarms: sealed VMs (Intel TDX) by the hour, USDC over x402.
Finance & CryptoPayments & trading
- Passed: Handshake
- Passed: Tools listed
- Passed: Updated recently
Median latency 514 ms · Last checked
Explore
Evidence for your next connection.
Independent measurements of remote MCP servers. Every observation has a timestamp.
Read-only probesMCP server · Payments & trading
Inspect servers, storage, networks, databases and billing, and start, stop or back up servers.
0 failed · 8 not measured
Median of successful probes over 7 days
Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.
Tool definitions returned by this server
Independent monitoring
Responded
The server completed its last measured handshake. This is an observation, not a guarantee.
Last checked| Test area | Passed | Failed | Unmeasured |
|---|---|---|---|
ConnectionCan a client connect and discover tools? | 5 | 0 | 0 |
Reliability & speedDoes it respond consistently and quickly? | 0 | 0 | 4 |
Access & authenticationWhat is required to use this server? | 1 | 0 | 2 |
Tool qualityAre the tool definitions usable by an agent? | 4 | 0 | 0 |
Publisher identityCan the publisher be traced to its source? | 4 | 0 | 2 |
Unmeasured means there is not enough evidence to decide. How these checks work
Start using UpCloud MCP by usefulapi
Choose your client, copy the configuration, then enable the server in your client’s MCP settings.
Run this command in your terminal, then restart Claude Code.
Claude Code
claude mcp add --transport http upcloud-mcp-by-usefulapi https://upcloud.usefulapi.io/mcpCapabilities
Take an on-demand, point-in-time backup of a storage device. Additive (nothing is overwritten) but backups are billed per GB. Asynchronous: the storage goes to a backuping/maintenance state and back to online — poll upcloud_get_storage. UpCloud: POST /1.3/storage/{uuid}/backup.
DiscoveredThe calling account: username, remaining credits and resource limits (cores, memory, storage per tier, IPs, networks, managed services). A cheap way to confirm the token works. UpCloud: GET /1.3/account.
DiscoveredBilling summary for one month with per-resource details (servers, storages, managed databases, object storage, …: amount, hours, plan, zone, labels) and totals. Needs an account allowed to read billing. UpCloud: GET /1.3/account/billing/summary/{yearmonth}.
DiscoveredFull details of one server: state, plan, cores/memory, network interfaces and IP addresses, attached storage devices, firewall on/off, simple-backup schedule, labels, tags and remote-access settings. UpCloud: GET /1.3/server/{uuid}.
DiscoveredDetails of one storage: size, tier, state (e.g. online, backuping), encryption, the servers it is attached to, its backups and backup_rule. Poll this to follow a backup started with upcloud_create_storage_backup. UpCloud: GET /1.3/storage/{uuid}.
DiscoveredSecurity audit trail of the account (up to 180 days): who did what to which resource, when, from which IP and via API or Hub. Filter by action, origin, resource type, time window or a keyword (UUID, username or IP). Returns total_count for paging. UpCloud: GET /1.3/audit-logs.
DiscoveredManaged Database services (PostgreSQL, MySQL, Valkey, OpenSearch): uuid, title, type, plan, zone, state, component hosts/ports, backups and labels. Note the response can include connection URIs with credentials. UpCloud: GET /1.3/database.
DiscoveredThe firewall rules of one server in evaluation order (position, direction, action, family, protocol, address and port ranges, comment). Whether the firewall is enabled at all is the `firewall` field of upcloud_get_server. UpCloud: GET /1.3/server/{uuid}/firewall_rule.
DiscoveredEvery IP address on the account: address, family (IPv4/IPv6), access (public/utility/private), the server it is assigned to, zone, PTR record, floating flag and release policy. UpCloud: GET /1.3/ip_address.
DiscoveredManaged Kubernetes clusters: name, uuid, zone, plan, state, network/CIDR, control-plane IP filter, labels and node groups (plan, count, state). UpCloud: GET /1.3/kubernetes.
DiscoveredManaged Load Balancer services with their frontends, backends and members, networks, plan, zone, configured status and operational state. UpCloud: GET /1.3/load-balancer.
DiscoveredNetworks visible to the account — public, utility and private SDN networks — with their IP subnets, DHCP settings, routes, attached servers and peerings. Optionally only one zone. UpCloud: GET /1.3/network/.
DiscoveredManaged Object Storage (S3-compatible) services: uuid, name, region, configured status and operational state, public/private endpoints, custom domains and labels. UpCloud: GET /1.3/object-storage-2.
DiscoveredFixed-price server plans: name (e.g. 2xCPU-4GB), cores, memory, included storage size/tier and transfer, plus GPU model/amount for GPU plans. UpCloud: GET /1.3/plan.
DiscoveredThe price list per zone in the account's currency: per-hour prices for plans, cores, memory, storage tiers, backups, IPv4 addresses and traffic. UpCloud: GET /1.3/price.
DiscoveredCloud servers on the account (summary: uuid, title, hostname, zone, plan, cores, memory, state, tags, labels). Filter by state, a free-text search (name, title, uuid, zone, IP, hostname, tag or template), tags or labels. Use upcloud_get_server for IPs and disks. UpCloud: GET /1.3/server.
DiscoveredStorage devices: disks, backups, CD-ROM images and OS templates (uuid, title, type, tier, size GB, state, zone, labels). Narrow by `kind`: private (yours), public (UpCloud-provided), normal (disks), backup, cdrom, template or favorite. UpCloud: GET /1.3/storage[/{kind}].
DiscoveredAvailable zones (data centres) with id (e.g. fi-hel1, de-fra1, us-chi1), description and whether they are public or private-cloud. Zone ids are used by every other resource. UpCloud: GET /1.3/zone.
DiscoveredChange a server's title, hostname and/or simple-backup schedule. Only these reversible fields are exposed — no resizing or plan change (billing) and no firewall toggle. simple_backup is `HHMM,daily|dailies|weeklies|monthlies` (UTC time) or `no` to disable. UpCloud: PUT /1.3/server/{uuid}.
DiscoveredDISRUPTIVE: stop and start a running server. soft (default) needs a timeout: after it, timeout_action=destroy hard-stops and restarts, ignore (API default) aborts and leaves the server running. hard power-cycles immediately. UpCloud: POST /1.3/server/{uuid}/restart.
DiscoveredStart a stopped server (billing for a started server resumes). Fails with 409 if it is not stopped. `async` returns immediately — poll upcloud_get_server for state=started. UpCloud: POST /1.3/server/{uuid}/start.
DiscoveredDISRUPTIVE: stop a running server — it goes offline until started again with upcloud_start_server. soft (default) sends an ACPI shutdown; with a timeout, a hard stop follows if it is still running. hard is like pulling the plug and can lose unsaved data. UpCloud: POST /1.3/server/{uuid}/stop.
DiscoveredRecent measurements
| Checked | Result | Response | Tools |
|---|---|---|---|
| Connected | 57 ms | 22 |