mountable.io

Create a filesystem and return it; its id is what tickets and mounts need. Needs a management key (mtblm_) or the login of an owner or admin; an API key gets management_key_required. org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. Not idempotent, and names need not be unique: after a timeout or an unknown outcome, call list_filesystems and look for the name before creating again. Never retry blindly. On rate_limited, wait retry_after seconds before retrying.

Create a one-time mount ticket for a sandbox. The result is the mount session with its ticket (single use, valid for minutes) and mount_command, a convenience hint for a person. Agents must construct the documented mountable mount --ticket-stdin --json command with separately quoted arguments, not evaluate mount_command. Pass the ticket through stdin from MOUNTABLE_TICKET, never in an argument list or log. /mnt/mountable is only a default: use a caller-approved writable directory. Use an existing approved CLI; if installation is authorized, choose npm install --global --ignore-scripts mountable-cli or uv tool install mountable, then mountable version. Report setup blockers instead of using sudo or a remote shell installer. Linux mounts need FUSE. Validate the nonempty ticket and selected filesystem ID, then wait for a mounted JSON event matching the intended path, filesystem and mode before using the directory. Retries: pass your own idempotency_key and reuse it when retrying after an unknown outcome. A replay returns the existing session without a ticket. If that session is still requested, its ticket was lost: this tool revokes it and creates a new one with a fresh key, and the result names the old one as replaced_session_id. If it is active or later, the ticket was used: nothing is revoked and the tool fails with ticket_already_used; use a new idempotency_key for another mount. idempotency_conflict means an identical request is in progress. If the outcome is unknown (network_error or outcome_unknown), the error's idempotency_key is the key that request was sent with: retry with exactly that key, even if you did not choose it. On rate_limited, wait retry_after seconds before retrying.

Remove a grant; sessions that relied on it end. Not idempotent: after an unknown outcome, call list_grants to see whether it is gone. Needs a management key (mtblm_) or the login of an owner or admin; an API key gets management_key_required. org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. On rate_limited, wait retry_after seconds before retrying.

Delete a webhook; deliveries to its URL stop. Not idempotent: after an unknown outcome, call list_webhooks to see whether it is gone. org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. On rate_limited, wait retry_after seconds before retrying.

Re-enable a webhook disabled after 24 hours of failed deliveries (disabled_reason failing), once its endpoint works again; the next delivery is usually a files.resync. A webhook disabled as access_revoked cannot be re-enabled (error access_revoked): create a new one with `mountable webhooks create`. Safe to retry. org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. On rate_limited, wait retry_after seconds before retrying.

A filesystem's stored bytes and files against its quotas, and its traffic over 30 days. org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. Read-only and safe to retry. On rate_limited, wait retry_after seconds before retrying.

List the organisation's API keys: id, name, filesystem_id (set for a key limited to one filesystem), expires_at and revoked; never their secrets. Creating a key is not a tool, because its answer is the key's secret: run `mountable api-keys create` or `mountable s3-keys create` (or use the SDKs) where the backend stores it. Needs a management key (mtblm_) or the login of an owner or admin; an API key gets management_key_required. org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. Read-only and safe to retry. On rate_limited, wait retry_after seconds before retrying.

List the organisation's filesystems (an API key sees those it has a grant on; a management key sees all). org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. Read-only and safe to retry. On rate_limited, wait retry_after seconds before retrying.

List a filesystem's grants: id, principal_type (member, group or api_key), principal_id and mode (ro or rw). Needs a management key (mtblm_) or the login of an owner or admin; an API key gets management_key_required. org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. Read-only and safe to retry. On rate_limited, wait retry_after seconds before retrying.

List a filesystem's live mount sessions (an API key sees those it created). org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. Read-only and safe to retry. On rate_limited, wait retry_after seconds before retrying.

List the caller's mountable.io organisations (a key has exactly one). Read-only and safe to retry. On rate_limited, wait retry_after seconds before retrying.

List a filesystem's S3 keys: access_key_id, name, mode, expires_at and revoked; never their secrets. The bucket is the filesystem ID at https://s3.mountable.io (path-style). Creating a key is not a tool, because its answer is the key's secret: run `mountable api-keys create` or `mountable s3-keys create` (or use the SDKs) where the backend stores it. Needs a management key (mtblm_) or the login of an owner or admin; an API key gets management_key_required. org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. Read-only and safe to retry. On rate_limited, wait retry_after seconds before retrying.

List a filesystem's webhooks: url, path_prefix, state (active or disabled), disabled_reason (failing or access_revoked) and the last delivery's outcome (last_success_at, last_failure, failing_since). Needs read-write access to the filesystem. Creating a webhook and rotating its secret are not tools, because their answer is the signing secret: run `mountable webhooks create` or `rotate-secret` (or use the SDKs) where the receiving backend stores it. org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. Read-only and safe to retry. On rate_limited, wait retry_after seconds before retrying.

Revoke an API key; its sessions end and its calls fail. Idempotent and safe to retry. Needs a management key (mtblm_) or the login of an owner or admin; an API key gets management_key_required. org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. On rate_limited, wait retry_after seconds before retrying.

Revoke a mount session; its mount stops working. Idempotent and safe to retry. On rate_limited, wait retry_after seconds before retrying.

Revoke an S3 key; S3 refuses it within 15 seconds. Idempotent and safe to retry. Needs a management key (mtblm_) or the login of an owner or admin; an API key gets management_key_required. org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. On rate_limited, wait retry_after seconds before retrying.

Give a member, group or API key access to a filesystem, or change the mode of its grant. Sets the same grant when repeated, so it is safe to retry. Needs a management key (mtblm_) or the login of an owner or admin; an API key gets management_key_required. org_id is optional: a key uses its own organisation, and a login with one organisation uses that one. On rate_limited, wait retry_after seconds before retrying.