Should my agent depend on the MCP server ai.borealhost/mcp?

Verdict: allow — rich-solo — safe to depend on As of 2026-08-15T11:28:18Z: a dated observation with receipts, not a warranty.

BorealHost

ai.borealhost/mcp

Agent-native web hosting — deploy sites, manage DNS, register domains, scale infrastructure

— the operator's own registry description reported

Publisher ai.borealhost · first seen 2026-08-12 · endpoint https://borealhost.ai/mcp/

allow

verdict

rich-solo

cluster

ok_tools

answers

144

tools served

Dependency rating derived

allow — rich-solo — safe to depend on

Cluster rich-solo · distinctiveness 0.658 (unusual). Every figure is a percentile or class within the 11,094-server census — see the whole spectrum.

Reach — can an agent get to it?

answersalive_tools

latency192 ms

vs populationtypical

protocolcurrent

authopen

Use — can it use it?

tools144

vs populationhigh

capabilities4

harnessB

Trust — can it rely on it?

identitysolo

servers on its host1

verifiabilityunassessed

duplicate inventoryno

drift events0

answers trueno primary

🔏 Signed receipt rr_fbd6e489a3a5f6404cf94a9e · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Tools last seen

add_cron add_domain_dns add_firewall_rule add_redirect add_ssh_key add_subdomain adopt_compute_instance attach_compute_volume cache_flush cache_status cache_toggle cancel_scheduled_snapshot claim_api_key cloudflare_proxy_status cloudflare_purge_cache cloudflare_set_proxy complete_checkout container_action create_alert_rule create_api_key create_b2_snapshot create_backup create_checkout create_compute_volume create_directory create_ftp_account create_mailbox create_snapshot create_support_ticket create_webhook database_search_replace decommission delete_account delete_alert_rule delete_backup delete_compute_volume delete_cron delete_domain_dns delete_file delete_mailbox delete_redirect delete_snapshot delete_webhook detach_compute_volume domain_detail domain_settings enable_smtp_relay enable_wildcard execute_query get_app_status get_backup_retention get_billing_portal get_checkout_status get_compute_instance get_compute_volume get_database_info get_email_status get_logs get_metrics get_resource_snapshot get_site_status get_smtp_relay get_snapshot_usage get_ssh_info get_stack_info get_support_ticket get_webmail_url install_app launch_compute_instance link_domain list_alert_rules list_api_keys list_apps list_backups list_compute_images list_compute_instances list_compute_types list_compute_volumes list_cron list_databases list_db_users list_domain_dns list_domains list_files list_firewall_rules list_ftp_accounts list_modules list_php_versions list_plans list_plugins list_redirects list_snapshots list_subdomains list_subscriptions list_support_tickets list_tables list_themes list_webhooks manage_db_user manage_dns manage_plugin manage_theme optimize_database read_file reboot_compute_instance register register_domain remove_firewall_rule remove_ftp_account reply_support_ticket request_api_key reset_mailbox_password restore_backup revoke_api_key revoke_smtp_relay rollback_snapshot rotate_key run_malware_scan scale schedule_snapshot search_domain set_api_key set_backup_retention set_domain_usage set_force_https setup_email snapshot_compute_volume ssl_info ssl_renew start_compute_instance stop_compute_instance switch_php terminate_compute_instance test_webhook toggle_module transfer_out_domain update_account update_checkout upload_file upload_ssl_cert whoami wp_check_updates wp_update_all write_file

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band B — usable, with rough edges.

legibility check	tools passing	ok
name is clear & specific	144/144	✓
has a description	144/144	✓
description is substantive	144/144	✓
parameters are typed	144/144	✓
parameters are described	9/144	9/144

144 of 144 tools graded · 144 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

Not in the Tier-2 trade lane, or not yet checked. Tier-2 re-derives a server's answers against published primary sources — see truth checks.

Protocol conformance observed

2025-06-18

protocol version

—

session model

1.27.0

server version BorealHost

Capabilities: experimental prompts resources tools

Drift

No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.

History observed

Every probe we made, oldest → newest (2 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (1 events)

date	type	what changed
2026-08-12	outcome	first probe: ok_tools

raw probe records

probed (UTC)	outcome	http	ms	protocol
2026-08-14T19:57:34Z	ok_tools	200	192	2025-06-18
2026-08-12T05:32:52Z	ok_tools	200	174	2025-06-18

Watch or embed this verdict

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/ai.borealhost/mcp.svg)](https://robinsaige.com/s/ai.borealhost/mcp)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview