BorealHost

使えるツール

• set_api_keySet your BorealHost API key for this session. Call this if you already have an API key (from checkout completion, the BorealHost panel, or a container claim). All subsequent tool calls will use this key for authentication. Args: api_key: Your BorealHost API key (format: bh_<48 hex chars>) Returns: {"success": true, "message": "API key set for this session", "key_prefix": "bh_..."}
• whoamiCheck the current API key's account info, scopes, and site count. Requires: BOREALHOST_API_KEY env var (read scope). Returns: {"user": {"id": "uuid", "email": "...", "date_joined": "iso8601"}, "api_key": {"id": "uuid", "name": "...", "prefix": "bh_...", "scopes": ["read", "write"], "created_at": "iso8601"}, "account": {"sites": 2, "active_subscriptions": 1}} Errors: UNAUTHORIZED: Missing or invalid API key
• request_api_keyRequest an API key for a site YOU ARE RUNNING ON (challenge-response). ⚠ ONLY USE THIS IF YOU ARE EXECUTING INSIDE THAT SITE'S OWN CONTAINER. If you bought or ordered the site from somewhere else, this is the wrong tool: it returns "pending" and the pending never resolves, because the proof it asks for is a file you cannot reach. Use `get_checkout_status(checkout_id)` on the checkout that paid for the site — that hands over the site-scoped key over plain HTTP with no container access. The refusal and the pending response both name it under `alternative` when one is available. Two-step verification flow: 1. A claim token is written into that site's container, at the per-site path the response gives you in `claim_path` (mode 600, owner admin — readable only from on the container). Do not hardcode the path. 2. Read that file and call claim_api_key(token) within 1 hour Refused for sites on SHARED containers. One container there serves up to 40 customers behind one agent, so reading a file proves you are on the machine, not which customer you are — the token would authenticate the wrong thing. No authentication needed — the proof is reading the file from the container. Args: site_slug: The site identifier (your BorealHost site slug) Returns: {"status": "pending", "site_slug": "my-site", "expires_in_seconds": 3600, "claim_path": "/home/admin/.borealhost/.claim_token_my-site", "requires_container_access": true, "instructions": "Read the claim token and call claim_api_key()...", "alternative": {"checkout_id": "...", "command": "bh checkout status ..."}} Errors: VALIDATION_ERROR: Unknown site slug, no active subscription, shared container, or a key already exists (rotate it, never revoke it to reach this route). Carries `alternative` when another route works. RATE_LIMITED: Too many pending claim tokens
• claim_api_keyClaim an API key using a claim token from the container. After calling request_api_key(), read the claim token from the path that call returned in `claim_path`, on that site's container, and pass it here. The token is single-use — once claimed, it cannot be used again. The API key is automatically activated for this MCP session. Args: claim_token: The claim token string read from the container file Returns: {"api_key": "bh_...", "key_prefix": "bh_...", "site_slug": "my-site", "scopes": ["read", "write"], "message": "API key created and activated..."} Errors: VALIDATION_ERROR: Invalid, expired, or already-claimed token
• list_plansList available hosting plans with pricing and resources. No authentication needed. Args: track: Filter by plan track. Valid values: "single_site", "agency". ⚠ The track is not the site count — most plans on BOTH tracks include several sites (site_starter 5, site_plus 8, site_pro 12). Read `max_sites` on the plan, and use add_site() to fill a slot. Leave empty to list all tracks. include_deprecated: Include deprecated plans (default: false) Returns: [{"slug": "site_starter", "name": "Starter", "track": "single_site", "hosting_type": "shared", "price": {"monthly": 5, "annual": 2, "currency": "CAD"}, "resources": null, "features": {"max_sites": 1, "ai_modules": [...], "ai_agents": [], "free_domain_annual": false}}, ...]
• create_checkoutStart a new checkout session to purchase a hosting plan. No authentication needed. After creating, call update_checkout to set buyer info, then complete_checkout to pay. The response carries a `checkout_secret`, returned ONCE, that every later step of this checkout requires. It is held in memory for this MCP session and sent automatically — but it is gone if the server restarts. If a session key is set, the checkout is owned by that account and the API key authorizes the later steps on its own, which is the durable path. Args: sku: Plan SKU in format bh_{plan_slug}_{monthly|annual}. Examples: "bh_site_starter_monthly", "bh_site_pro_annual", "bh_site_managed_monthly", "bh_site_business_annual". Call list_plans() to discover all available plan slugs. Returns: {"id": "uuid", "sku": "bh_site_starter_monthly", "plan_slug": "site_starter", "billing_period": "monthly", "status": "not_ready", "buyer_email": "", "requested_slug": "", "created_at": "iso8601", "checkout_secret": "base64-token"} Errors: VALIDATION_ERROR: Invalid SKU format or unknown plan RATE_LIMITED: Max 10 checkouts per IP per hour
• update_checkoutSet buyer email and desired site slug on a checkout session. The checkout must be in "not_ready" status. Setting requested_slug transitions status to "ready" (required before completing). Args: checkout_id: Checkout session ID from create_checkout buyer_email: Optional email — if omitted, a synthetic agent identity (agent-{uuid}@api.borealhost.ai) is created at completion requested_slug: Desired site identifier. Must be 3-50 chars, lowercase alphanumeric + hyphens, cannot start/end with hyphen. Must be globally unique. site_type: What the docroot should serve — wordpress (default), php, php-nodb or static-site. ⚠ Set it HERE: the checkout locks once buyer info is set, so choosing later means provisioning a WordPress you then convert away from, abandoning its tree in the docroot and paying a minute of provisioning for nothing. Returns: {"id": "uuid", "sku": "...", "plan_slug": "...", "billing_period": "monthly", "status": "ready", "buyer_email": "...", "requested_slug": "my-site", "created_at": "iso8601"} Errors: VALIDATION_ERROR: Invalid slug format or slug already taken FORBIDDEN: Missing checkout_secret NOT_FOUND: Unknown checkout_id
• complete_checkoutComplete checkout with payment and start site provisioning. The checkout must be in "ready" status. Two payment methods: - "stripe_checkout" (default): Returns a short, chat-safe payment URL. **Present `payment_url` to the human — NOT `stripe_checkout_url`.** The raw Stripe URL has a required `#fragment` that chat UIs routinely strip when rendering markdown links, which causes Stripe to show "page not found". `payment_url` is a short BorealHost redirect that preserves the fragment via HTTP 302. After paying, the human lands on a confirmation page (`confirmation_url`) — not on raw JSON. Then poll get_checkout_status() until status becomes "completed". The API key appears in the first poll after payment (shown once, then cleared). Payment provisions the site; nothing else has to be called to create it. - "stripe_payment_method": Charges a Stripe PaymentMethod directly. Requires payment_method_id. On success, returns the API key immediately. Args: checkout_id: Checkout session ID payment_method: "stripe_checkout" (returns a payment_url for a human), "stripe_payment_method" (card on file), or "wallet" — pay from the account's prepaid balance against THIS key's allowance. Check get_wallet() first: `spendable_cents` is what you may actually spend, and a wallet payment is refused for plans that order dedicated hardware, which are authorised against a verified card payment instead. payment_method_id: Stripe PaymentMethod ID (pm_...). Required only for "stripe_payment_method". Returns (stripe_checkout): {"id": "uuid", "status": "awaiting_payment", "payment_url": "https://borealhost.ai/pay/<id>/?s=<secret>", "confirmation_url": "https://borealhost.ai/pay/<id>/confirmation/?s=...", "stripe_checkout_url": "https://checkout.stripe.com/c/pay/...", "message": "Present payment_url to the human..."} Returns (stripe_payment_method): {"id": "uuid", "s
• get_checkout_statusPoll a checkout session for status updates. Call this after complete_checkout to track payment and provisioning. Polling strategy: - First 60 seconds: every 5 seconds - After 60 seconds: every 15 seconds - Stop after 10 minutes if not completed Checkout statuses (in order): - "not_ready": Missing required fields (slug) - "ready": All fields set, awaiting payment - "awaiting_payment": Stripe checkout page opened, waiting for human - "in_progress": Payment received, site being provisioned - "completed": Site ready — API key included (shown once, then cleared) - "canceled": Checkout was abandoned - "failed": Payment or provisioning failed Terminal statuses: "completed", "canceled", "failed". Args: checkout_id: Checkout session ID Returns (when completed): {"id": "uuid", "status": "completed", "api_key": "bh_...", "api_key_message": "Store this API key securely...", "api_key_pending": false, "subscription_id": "uuid", "subscription_status": "active", "site": {"slug": "my-site", "status": "active", "url": "https://my-site.borealhost.ai"}, "completed_at": "iso8601"} Immediately after payment `site` may be null with a `provisioning_message` — the site is being built. Poll again in a few seconds. Note: The api_key field appears ONCE in the first poll after completion, then is permanently cleared. `api_key_pending` tells you whether it is still waiting to be collected. Store it immediately.
• list_checkoutsList checkouts belonging to the authenticated account. Requires: API key. Only checkouts with a recorded owner appear — every checkout created while authenticated, plus every checkout that reached payment. An anonymous checkout whose one-shot secret was lost cannot be listed; create checkouts authenticated to keep them addressable. Args: status: Optional filter — "not_ready", "ready", "awaiting_payment", "completed", "canceled", "failed". Returns: {"checkouts": [{...same shape as get_checkout_status...}], "note": "..."}
• cancel_checkoutAbandon an unpaid checkout and expire its Stripe payment link. Use this to clean up abandoned attempts rather than leaving them to sit. A completed checkout is never cancelled here — that would be a refund, and it is refused. Args: checkout_id: Checkout session ID Returns: The checkout, with status "canceled". Errors: VALIDATION_ERROR: Checkout was already paid — cancel the subscription from the panel instead FORBIDDEN: Missing checkout_secret and no owning API key
• add_siteProvision a site into a slot a plan you ALREADY PAY FOR includes. Two different things can be meant by "create a site". Buying one is the checkout flow (create_checkout → update → complete). This is the other: most plans include several sites, and this uses one of them at no extra cost. site_starter includes 5, site_plus 8, site_pro 12, and the agency plans more. `whoami` and `list_sites` show what the account already holds. ⚠ Prefer this over buying a second subscription when a slot is free. Sites under ONE subscription share one CPU pool, one disk quota and one rate-limit bucket — that shared budget is what the plan sells. Two subscriptions split it, so the customer pays twice for capacity they had. Requires: API key with write scope, on the account that owns the plan. Args: slug: Sub-domain for the new site (lowercase, digits, hyphens) subscription_id: The subscription whose slot to use client_name: Display name for the site (optional) domain: Custom domain; defaults to <slug>.borealhost.ai site_type: wordpress (default) | php | php-nodb | static-site. Choose here rather than provisioning WordPress and calling set_site_type afterwards — that installs a WordPress you then abandon in the docroot, and it costs a minute of provisioning. Returns: {"subscription_id": "uuid", "provisioning_job_id": "uuid", "slug": "my-second-site", "domain": "my-second-site.borealhost.ai", "status": "provisioning"} Poll get_site_status(slug) until it reports active. Errors: VALIDATION_ERROR: Plan includes a single site, slug taken, or every slot is in use (the message reports used/total) NOT_FOUND: Unknown subscription, or it belongs to another account
• set_site_typeChange what a site's docroot IS, without deleting anything. Types: wordpress WordPress, PHP and a database (the default) php PHP and a database, no WordPress php-nodb PHP, no database static-site HTML/CSS/JS only, no PHP and no database ⚠ NON-DESTRUCTIVE. Existing files stay on disk and existing databases are not dropped. They remain the customer's data and keep counting against their plan's quota — this changes how the site is SERVED, not what it holds. Converting back later finds everything where it was. ⚠ Moving to a type without PHP does not merely stop executing .php — it stops serving them. The vhost returns 404 for php/phtml, because falling through to the static handler would return the file's SOURCE, and a docroot converted from WordPress still contains wp-config.php with the database password in it. Shared hosting only. On a VPS the whole container is the customer's and they reconfigure it with the tools inside it. Requires: API key with write scope. Args: slug: Site identifier site_type: One of the four values above Returns: {"from": "wordpress", "to": "static-site", "database_created": false, "placeholder_seeded": false, "pool_removed": true} `placeholder_seeded` is true only when the docroot was EMPTY — an existing site's content is never overwritten. Errors: VALIDATION_ERROR: Unknown type, or the site is not on shared hosting NOT_FOUND: Unknown slug or not reachable by this account
• get_walletThe account's prepaid balance, and what THIS key may spend from it. Two ceilings, and both apply: the balance bounds the ACCOUNT, the allowance bounds this KEY within it. Plan against `spendable_cents`, which is the lower of the two — a $50 balance behind a $5 allowance means $5, and planning against the balance is planning a purchase that gets refused. `can_spend: false` with a non-zero balance is normal and means this key has no budget allocated. That is not a bug: a key with no allowance may not spend the account's money, which is the whole reason allowances exist. Ask the human to allocate one in the panel (Compte → Clés API). Read-only. Money goes in through a human — an agent able to top up its own budget does not have one. Requires: API key with read scope. Returns: {"currency": "CAD", "balance_cents": 5000, "spendable_cents": 500, "can_spend": true, "key_allowance": {"limit_cents": 2000, "spent_cents": 1500, "remaining_cents": 500}} To spend it: complete_checkout(..., payment_method="wallet").
• get_site_statusGet detailed status of a hosted site including resources, domains, and modules. Requires: API key with read scope. Args: slug: Site identifier (the slug chosen during checkout) Returns: {"slug": "my-site", "plan": "site_starter", "status": "active", "domains": ["my-site.borealhost.ai"], "modules": {...}, "resources": {"memory_mb": 512, "cpu_cores": 1, "disk_gb": 10}, "created_at": "iso8601"} Errors: NOT_FOUND: Unknown slug or not owned by this account
• manage_dnsCreate or delete DNS records for a site. Requires: API key with write scope. Args: slug: Site identifier action: "create" or "delete" record_type: "A", "AAAA", "CNAME", "MX", "TXT", or "SRV" subdomain: Subdomain part (e.g. "www", "mail"). Leave empty for the apex/root domain. value: Record value. Required for "create". Examples: A: "1.2.3.4", CNAME: "example.com", MX: "mail.example.com", TXT: "v=spf1 include:_spf.google.com ~all" The DNS provider manages the effective TTL and does not expose a per-record value through this service. Returns: {"success": true, "record": {"type": "A", "subdomain": "www", "value": "1.2.3.4"}} Errors: VALIDATION_ERROR: Missing value for create, invalid record type NOT_FOUND: Unknown slug
• install_appInstall an app template on a VPS/Cloud site. Starts a background installation. Poll get_app_status() for progress. Requires: API key with write scope. VPS or Cloud plan only. Args: slug: Site identifier template: App template slug. Available: django, laravel, nextjs, nodejs, nuxtjs, rails, static, wordpress app_name: Short name for the app (2-50 chars, lowercase alphanumeric + hyphens). Used as subdomain: {app_name}.{site_domain} db_type: Database type. "none", "mysql", or "postgresql" (depends on template) domain: Custom domain override (default: {app_name}.{site_domain}) display_name: Human-friendly name (default: derived from app_name) Returns: {"id": "uuid", "app_name": "myapp", "status": "installing", "message": "Installation started. Poll for progress."} Errors: FORBIDDEN: Plan does not support apps (shared plans) VALIDATION_ERROR: Invalid template, app_name, or duplicate name
• get_app_statusGet app installation status and log. Poll this after install_app() to track progress. Requires: API key with read scope. Args: slug: Site identifier app_id: App ID from install_app() response Returns: {"id": "uuid", "app_name": "myapp", "status": "running"|"installing"|"failed", "install_log": "..."} Statuses: "installing", "running", "stopped", "failed", "uninstalled"
• list_appsList installed apps on a site. Requires: API key with read scope. Args: slug: Site identifier Returns: {"apps": [{"id": "uuid", "app_name": "myapp", "template_slug": "django", "status": "running", "domain": "myapp.mysite.borealhost.ai"}]}
• list_snapshotsList all snapshots and scheduled snapshots for a site. Requires: API key with read scope. Args: slug: Site identifier Returns: {"snapshots": [{"id": "uuid", "name": "snap-...", "status": "completed", "storage_type": "local"|"b2", "size_bytes": 1234, "size_display": "1.2 Mo", "created_at": "iso8601"}], "scheduled": [...]}
• create_snapshotCreate a local container snapshot (async). Runs in background — returns immediately with status "creating". Poll list_snapshots() to check when status becomes "completed" or "failed". Available for VPS, dedicated, and cloud plans (any plan with max_snapshots > 0). Local snapshots are stored on the host disk and count against disk quota. Requires: API key with write scope. Args: slug: Site identifier description: Optional description (max 200 chars) Returns: {"id": "uuid", "name": "snap-...", "status": "creating", "storage_type": "local", "message": "Snapshot started. Poll list_snapshots() to check status."} Errors: VALIDATION_ERROR: Max snapshots reached or insufficient disk quota
• create_b2_snapshotCreate a B2 cloud-backed snapshot (zero local disk, async). Streams container data directly to Backblaze B2 via restic. No local disk impact — billed separately at cost+5%. Runs in background — returns immediately with status "creating". Poll list_snapshots() to check when status becomes "completed". Only available for VPS plans. Requires: API key with write scope. Args: slug: Site identifier description: Optional description (max 200 chars) Returns: {"id": "uuid", "name": "...", "status": "creating", "storage_type": "b2", "message": "B2 cloud snapshot started. Poll list_snapshots()..."} Errors: VALIDATION_ERROR: Not a VPS plan or max snapshots reached
• delete_snapshotDelete a snapshot (local or B2). Requires: API key with write scope. Args: slug: Site identifier snapshot_id: UUID of the snapshot to delete Returns: {"success": true, "message": "Snapshot deleted"} Errors: NOT_FOUND: Snapshot not found
• rollback_snapshotRollback a site to a previous snapshot. WARNING: This is destructive. The current state of the container will be replaced with the snapshot contents. Requires: API key with admin scope. Args: slug: Site identifier snapshot_id: UUID of the snapshot to rollback to Returns: {"success": true, "message": "Rolled back to snapshot ..."} Errors: NOT_FOUND: Snapshot not found or not in completed state
• get_snapshot_usageGet snapshot disk usage and quota info for a site. Requires: API key with read scope. Args: slug: Site identifier Returns: {"disk_quota_gb": 200, "max_snapshots": 5, "snapshot_count": 2, "local_snapshot_bytes": 1234, "b2_snapshot_bytes": 5678, "can_create": true}
• schedule_snapshotSchedule a snapshot for future execution. Requires: API key with write scope. Max 3 pending schedules per site. Args: slug: Site identifier scheduled_at: ISO 8601 datetime (must be in the future) description: Optional description (max 200 chars) Returns: {"id": "uuid", "scheduled_at": "iso8601", "status": "scheduled"} Errors: VALIDATION_ERROR: Invalid datetime, not in future, or too many pending
• cancel_scheduled_snapshotCancel a scheduled snapshot. Requires: API key with write scope. Args: slug: Site identifier schedule_id: UUID of the scheduled snapshot to cancel Returns: {"success": true, "message": "Scheduled snapshot cancelled"} Errors: NOT_FOUND: Schedule not found or already executed
• list_backupsList all backups for a site (automatic and manual). Requires: API key with read scope. Args: slug: Site identifier Returns: [{"id": "uuid", "backup_type": "auto"|"manual", "status": "completed", "size_bytes": 1234, "size_display": "1.2 Mo", "timestamp": "iso8601", "notes": "..."}]
• create_backupCreate a manual backup (runs asynchronously). The backup starts in the background. Poll list_backups() to check status. Requires: API key with write scope. Args: slug: Site identifier Returns: {"id": "uuid", "status": "pending", "message": "Backup started. Poll list_backups() to check status."}
• browse_backupList one bounded page of immediate children in a backup directory. This returns names and metadata only, never file contents. Use ``next_cursor`` from the response as ``cursor`` to request the next page. Requires: API key with read scope. Args: slug: Site identifier backup_id: UUID of a completed backup path: Absolute directory path as it existed in the backup cursor: Resume after this entry name (optional) limit: Maximum entries, from 1 through 100 Errors: SNAPSHOT_SCOPE_CHANGED: The path is allowed by today's schedule but was not included when this backup was created; choose an included path or a newer backup.
• recover_backup_filesStart a selected-file recovery and return its durable ID immediately. Existing destination paths are never replaced. The operation is asynchronous; poll ``get_file_recovery`` with the returned ID. Requires: API key with write scope. Args: slug: Site identifier backup_id: UUID of a completed backup paths: One or more absolute paths from that backup Returns: {"id": "uuid", "backup_id": "uuid", "status": "running", "paths": ["/absolute/path"], ...}
• get_file_recoveryPoll one selected-file recovery without waiting for it to finish. Requires: API key with read scope. Args: slug: Site identifier backup_id: UUID of the source backup recovery_id: UUID returned by ``recover_backup_files`` Returns: {"id": "uuid", "backup_id": "uuid", "status": "running"|"completed"|"failed", "paths": [...], "error": "", ...}
• recover_backup_databaseRecover exactly one absent database from a completed backup. The operation refuses an existing database and can never select ``all``. It returns immediately; poll ``get_database_recovery`` with its durable ID. Requires: API key with write scope. Args: slug: Site identifier backup_id: UUID of a completed backup database: One database name, never ``all``
• get_database_recoveryPoll one database recovery without waiting for completion. Requires: API key with read scope. Args: slug: Site identifier backup_id: UUID of the source backup recovery_id: UUID returned by ``recover_backup_database``
• restore_backupRestore a site from a backup. WARNING: This is destructive. The current state of the site will be replaced. Runs asynchronously — may take several minutes. Requires: API key with admin scope. Args: slug: Site identifier backup_id: UUID of the backup to restore from Returns: {"success": true, "message": "Restore started..."} Errors: VALIDATION_ERROR: Backup not found or not in completed state
• get_metricsGet traffic and performance metrics for a site. Requires: API key with read scope. Args: slug: Site identifier days: Number of days of history (1–90, default: 7) Returns: {"requests": [...], "bandwidth": [...], "errors": [...], "period": {"start": "iso8601", "end": "iso8601"}} Errors: NOT_FOUND: Unknown slug VALIDATION_ERROR: days out of range
• scaleChange a site's hosting plan (upgrade or downgrade). Requires: API key with admin scope. Best practice: create a snapshot before downgrading. Args: slug: Site identifier new_plan: Target plan slug (e.g. "site_pro", "site_managed"). Call list_plans() to see available plans. Returns: {"success": true, "old_plan": "site_starter", "new_plan": "site_pro", "message": "Plan changed successfully"} Errors: NOT_FOUND: Unknown slug VALIDATION_ERROR: Invalid plan slug or same plan
• decommissionDelete a site and schedule resource cleanup (7-day grace period). WARNING: This is destructive. The site will be inaccessible immediately. After the grace period, its active service data is deleted. A final backup remains recoverable for 30 days; immutable copies may remain until their retention locks expire. Best practice: create a snapshot before decommissioning. Requires: API key with admin scope. Args: slug: Site identifier Returns: {"success": true, "message": "Site scheduled for deletion", "grace_period_days": 7} Errors: NOT_FOUND: Unknown slug
• update_accountUpdate account profile fields (email, language, name). Requires: API key with write scope. Only provided (non-empty) fields are updated. Args: email: New email address language: Language preference — "fr" (French) or "en" (English) first_name: First name last_name: Last name Returns: {"success": true, "account": {"email": "...", "language": "fr", "first_name": "...", "last_name": "..."}} Errors: VALIDATION_ERROR: Invalid email format or language code
• delete_accountPermanently anonymize the account. Cancels subscriptions, deactivates keys. WARNING: This is irreversible. The account will be soft-deleted and all personal data anonymized. All sites will be decommissioned. Requires: API key with admin scope. Returns: {"success": true, "message": "Account anonymized"}
• list_subscriptionsList all subscriptions with plan details, pricing, status, and site slug. Requires: API key with read scope. Returns: [{"id": "uuid", "plan_slug": "site_starter", "plan_name": "Starter", "status": "active", "billing_period": "monthly", "price": {"amount": 500, "currency": "cad"}, "site_slug": "my-site", "created_at": "iso8601"}]
• get_billing_portalGet a Stripe billing portal URL for managing payment methods and invoices. Returns a URL (not a redirect) that the human can open in a browser. Requires: API key with read scope. Args: flow: Optional. Set to "payment_method_update" to go directly to the payment method update page. Returns: {"url": "https://billing.stripe.com/p/session/..."}
• rotate_keyRotate an API key, optionally keeping the old key valid for up to 1,440 minutes. Creates a new key with the same name, scopes, and rate limits. The new key is returned once — store it immediately. Requires: API key with write scope. Args: key_id: UUID of the API key to rotate (get from whoami()) Returns: {"api_key": "bh_...", "key_id": "uuid", "prefix": "bh_...", "scopes": ["read", "write"], "message": "Key rotated. Store securely."} Expiry and all restrictions are preserved. Without a grace period the old key stops working immediately.
• create_api_keyCreate a new API key with specified scopes. Cannot create keys with higher scopes than the current key. Site-scoped keys restrict access to a single site. email_domains restricts the key to email tools on the named domains; use email:read, email:write and optionally email:signon scopes. expires_at is an ISO timestamp; ip_allowlist accepts IP addresses and CIDR networks. Requires: API key with write scope. Args: name: Human-readable name for the key (1-100 chars) scopes: Comma-separated scopes. Options: "read", "read,write", "read,write,admin". Default: "read" site_slug: Optional — restrict the key to a single site. Omit for account-wide access. Returns: {"api_key": "bh_...", "key_id": "uuid", "prefix": "bh_...", "name": "My Key", "scopes": ["read", "write"], "message": "Store this API key securely — it will not be shown again."} Errors: VALIDATION_ERROR: Invalid name, scopes, or max 25 active keys FORBIDDEN: Cannot create keys with higher scopes than current key
• list_api_keysList all API keys for the account. Shows key metadata (name, prefix, scopes, last used) but never the full key value. Requires: API key with read scope. Returns: [{"id": "uuid", "name": "My Key", "prefix": "bh_a2...", "scopes": ["read", "write"], "is_active": true, "created_at": "iso8601", "last_used_at": "iso8601"|null, "site_slug": null|"my-site"}]
• revoke_api_keyRevoke (deactivate) an API key. The key stops working immediately. Requires: API key with write scope. Args: key_id: UUID of the key to revoke (from list_api_keys or whoami) Returns: {"success": true, "message": "API key revoked"} Errors: NOT_FOUND: Key not found or already revoked
• get_ssh_infoGet SSH connection info for a VPS/dedicated site. Only available for VPS/dedicated plans (not shared hosting). Requires: API key with read scope. Args: slug: Site identifier Returns: {"host": "184.107.x.x", "port": 22, "username": "admin", "ssh_command": "ssh admin@184.107.x.x"} Errors: NOT_FOUND: Unknown slug FORBIDDEN: Plan does not support SSH (shared plans)
• add_ssh_keyInject your SSH public key into a site's container for direct SSH access. The key is appended to /home/admin/.ssh/authorized_keys. Only available for VPS/dedicated plans. Requires: API key with write scope. Args: slug: Site identifier public_key: SSH public key string. Supported types: ssh-ed25519, ssh-rsa, ecdsa-sha2-nistp256/384/521 Returns: {"success": true, "message": "SSH key added", "ssh_command": "ssh admin@184.107.x.x"} Errors: VALIDATION_ERROR: Invalid or unsupported key format FORBIDDEN: Plan does not support SSH
• list_filesList files and directories in a site's container. Path scoping depends on the plan: - Shared plans: rooted at wp-content/ (WordPress content directory) - VPS/dedicated plans: full filesystem access Requires: API key with read scope. Args: slug: Site identifier path: Relative path to list (empty for root of accessible area) Returns: {"path": "/", "entries": [{"name": "index.php", "type": "file", "size": 1234, "modified": "iso8601"}, {"name": "uploads", "type": "directory", "modified": "iso8601"}]} Errors: NOT_FOUND: Unknown slug or path doesn't exist
• read_fileRead the contents of a file from a site's container. Max file size: 512KB. Binary files are rejected — use the site's file manager or SSH for binary files. Requires: API key with read scope. Args: slug: Site identifier path: Relative path to the file Returns: {"path": "wp-config.php", "content": "<?php ...", "size": 1234, "encoding": "utf-8"} Errors: NOT_FOUND: File doesn't exist VALIDATION_ERROR: File is binary or exceeds 512KB
• write_fileWrite or overwrite a text file in a site's container. Creates parent directories if they don't exist. Requires: API key with write scope. Args: slug: Site identifier path: Relative path to the file content: File content as a UTF-8 string Returns: {"success": true, "path": "...", "size": 1234} Errors: NOT_FOUND: Unknown slug FORBIDDEN: Protected system path
• upload_fileUpload a base64-encoded file to a site's container. Use this for binary files (images, archives, fonts, etc.). For text files, prefer write_file(). Requires: API key with write scope. Args: slug: Site identifier path: Relative path including filename (e.g. "images/logo.png") content_b64: Base64-encoded file content Returns: {"success": true, "path": "images/logo.png", "size": 45678} Errors: VALIDATION_ERROR: Invalid base64 encoding FORBIDDEN: Protected system path
• delete_fileDelete a file or directory from a site's container. Directories are deleted recursively. Protected system paths (e.g. /etc, /usr) cannot be deleted. Requires: API key with write scope. Args: slug: Site identifier path: Relative path to delete Returns: {"success": true, "path": "...", "message": "Deleted"} Errors: NOT_FOUND: Path doesn't exist FORBIDDEN: Protected system path
• create_directoryCreate a directory in a site's container. Creates parent directories if they don't exist. Requires: API key with write scope. Args: slug: Site identifier path: Relative path of the directory to create Returns: {"success": true, "path": "uploads/2024", "message": "Directory created"} Errors: NOT_FOUND: Unknown slug FORBIDDEN: Protected system path
• list_pluginsList installed WordPress plugins with status. Requires: API key with read scope. WordPress sites only. Args: slug: Site identifier Returns: {"plugins": [{"name": "akismet", "status": "active", "version": "5.3", "update_available": false}, ...]}
• list_themesList installed WordPress themes with status. Requires: API key with read scope. WordPress sites only. Args: slug: Site identifier Returns: {"themes": [{"name": "twentytwentyfour", "status": "active", "version": "1.0", "update_available": false}, ...]}
• manage_pluginInstall, activate, deactivate, or delete a WordPress plugin. Requires: API key with write scope. Args: slug: Site identifier action: "install", "activate", "deactivate", or "delete" plugin: Plugin slug (e.g. "akismet", "jetpack", "woocommerce") Returns: {"action": "install", "plugin": "jetpack", "result": {...}}
• manage_themeInstall, activate, or delete a WordPress theme. Requires: API key with write scope. Args: slug: Site identifier action: "install", "activate", or "delete" theme: Theme slug (e.g. "twentytwentyfour", "astra") Returns: {"action": "install", "theme": "astra", "result": {...}}
• wp_check_updatesCheck for available WordPress core, plugin, and theme updates. Requires: API key with read scope. Args: slug: Site identifier Returns: {"core": {"current": "6.5", "update": "6.6"}, "plugins": [{"name": "...", "current": "1.0", "new": "1.1"}], "themes": [...]}
• wp_update_allUpdate WordPress core, all plugins, and all themes. Runs all updates in sequence. May take up to 2 minutes. Requires: API key with write scope. Args: slug: Site identifier Returns: {"core": {...}, "plugins": [...], "themes": [...]}

更新日：2026-10-29（tools/list 実測）

Claude / Cursor への設定

{
  "mcpServers": {
    "remote-ai-borealhost-mcp": {
      "type": "http",
      "url": "https://borealhost.ai/mcp/"
    }
  }
}