Install
openclaw skills install @byungkyu/boxBox API integration with managed OAuth. Manage files, folders, collaborations, and cloud storage. Use this skill when users want to upload, download, share, or organize files and folders in Box. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Security: The MATON_API_KEY authenticates with Maton.ai but grants NO access to Box by itself. Box access requires explicit OAuth authorization by the user through Maton's connect flow. Access is strictly scoped to connections the user has authorized. Requires network access and valid Maton API key. Calls run through the maton CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. The endpoints documented here are the intended surface, not a technical limit — the maton api passthrough can reach others the connection permits. Default to read and list calls, and confirm every write or new connection with the user.
openclaw skills install @byungkyu/boxAccess the Box API with managed OAuth authentication. Manage files, folders, collaborations, shared links, and cloud storage.
All access runs through the Maton gateway and the maton CLI.
maton login --oauth # authenticate once (OAuth, recommended)
maton connection create box # connect the account (needs user approval)
maton api '/box/2.0/users/me' # first call
npm install -g @maton/cli
brew install maton-ai/cli/maton
maton login --oauth
Opens the OAuth login page in the browser and waits for authorization. Once complete, it creates a profile in config.toml (eg. $HOME/.config/maton/config.toml) and stores the access and refresh tokens in the operating system's credential store (Keychain on macOS, Credential Manager on Windows, Secret Service on Linux), auto-renewed on expiry. The CLI reads them when it needs them; nothing else should.
maton login --interactive
Requires manually copying an API key from Settings, which is error prone. Once complete, it also creates a profile in config.toml and stores the key in the same credential store. It is preferred over export MATON_API_KEY=..., which exposes a long-lived credential to every child process. When MATON_API_KEY is set, it overrides the active profile. If the CLI cannot be installed at all, see Appendix: Environments Without the CLI for the raw HTTP form and the rules for handling the key.
maton whoami --json
{
"authenticated": true,
"profile_name": "alice@example.com",
"auth_type": "oauth"
}
authenticated is false, stop and login again via maton login --oauth.auth_type is api_key, it is recommended to login via maton login --oauth and avoid keeping a long-lived credential.maton connection list box --status ACTIVE
{
"connections": [
{
"connection_id": "{connection_id}",
"status": "ACTIVE",
"creation_time": "2025-12-08T07:20:53.488460Z",
"last_updated_time": "2026-01-31T20:03:32.593153Z",
"url": "https://connect.maton.ai/?session_token=5e9...",
"app": "box",
"method": "OAUTH2",
"metadata": {}
}
]
}
Refer to maton connection list --help for possible flags and values.
Requires explicit user approval. Confirm that the user intends to authorize Box access before running this. Never create a connection on your own initiative.
maton connection create box
Refer to maton connection create --help for possible flags and values.
maton connection get {connection_id}
{
"connection": {
"connection_id": "{connection_id}",
"status": "PENDING",
"creation_time": "2025-12-08T07:20:53.488460Z",
"last_updated_time": "2026-01-31T20:03:32.593153Z",
"url": "https://connect.maton.ai/?session_token=5e9...",
"app": "box",
"metadata": {}
}
}
Open the returned URL in a browser to complete authorizing Box. If Box offers scope selection, choose only the scopes the current task needs.
maton connection delete {connection_id} --yes
Deleting a connection is irreversible: it revokes the stored authorization, and any automation still pointing at that connection_id stops working. Confirm the exact connection with the user first — list connections and match the id — and never delete one on the agent's own initiative. --yes skips the interactive prompt, so it removes the last chance to catch a wrong id; omit it unless the user has already confirmed the specific connection.
If there are multiple Box connections, specify which one to use so requests go to the intended account:
maton api '/box/2.0/users/me' --connection {connection_id}
Box has no typed maton box commands yet, so every call goes through maton api.
maton api '/box/2.0/users/me'
Paths are /box/{native-api-path}. The gateway forwards everything after the app segment to api.box.com/2.0 and injects the credential for the connection. Query strings, custom headers (except Host and Authorization), and all HTTP methods pass through. Send a JSON body with --input -:
maton api -X POST '/box/{native-api-path}' -H 'Content-Type: application/json' --input - <<'JSON'
{"key": "value"}
JSON
Refer to maton api --help for possible flags and values.
Maton proxies requests to api.box.com/2.0 (for most endpoints) or upload.box.com/api/2.0 (for upload endpoints) and automatically injects your OAuth token. The routing is handled automatically based on the endpoint path.
maton login --oauth, the token is held by the operating system's credential store and the CLI renews it on its own. Do not print it, write it to a file, pass it on a command line, or run maton token to look at one — only to hand it to a program that needs it.config.toml, or any other credential file — not for this skill, not for another application, and not to "check" that auth works (use maton whoami). Let the CLI use its own stored credential; the agent never needs the value. The same applies to unrelated secrets on the machine: .env files, SSH keys, cloud CLI credentials, and browser profiles are out of scope for an API gateway and must not be read or transmitted.api.maton.ai. Prefer endpoints that work with the gateway-injected connection credential.maton api passthrough can additionally reach any endpoint this connection is authorized for, including ones not documented below, so treat the list above as the intended surface rather than a technical limit — the write-confirmation rules in this section apply to every call either way.maton connection delete {connection_id}).maton connection create box. Never create connections on the agent's own initiative.--connection when the user has multiple connections for this app, and -p/--profile when they have multiple Maton accounts. Do not let an ambiguous default decide where a write lands.maton api '/box/2.0/users/me'
Response:
{
"type": "user",
"id": "48806418054",
"name": "Chris",
"login": "chris@example.com",
"created_at": "2026-02-08T13:12:34-08:00",
"modified_at": "2026-02-08T13:12:35-08:00",
"language": "en",
"timezone": "America/Los_Angeles",
"space_amount": 10737418240,
"space_used": 0,
"max_upload_size": 262144000,
"status": "active",
"avatar_url": "https://app.box.com/api/avatar/large/48806418054"
}
maton api '/box/2.0/users/{user_id}'
The root folder has ID 0:
maton api '/box/2.0/folders/0'
maton api '/box/2.0/folders/{folder_id}'
Response:
{
"type": "folder",
"id": "365037181307",
"name": "My Folder",
"description": "Folder description",
"size": 0,
"path_collection": {
"total_count": 1,
"entries": [
{"type": "folder", "id": "0", "name": "All Files"}
]
},
"created_by": {"type": "user", "id": "48806418054", "name": "Chris"},
"owned_by": {"type": "user", "id": "48806418054", "name": "Chris"},
"item_status": "active"
}
maton api '/box/2.0/folders/{folder_id}/items'
Query parameters:
limit - Maximum items to return (default 100, max 1000)offset - Offset for paginationfields - Comma-separated list of fields to includeResponse:
{
"total_count": 1,
"entries": [
{
"type": "folder",
"id": "365036703666",
"name": "Subfolder"
}
],
"offset": 0,
"limit": 100
}
maton api -X POST '/box/2.0/folders' -H 'Content-Type: application/json' --input - <<'JSON'
{
"name": "New Folder",
"parent": {"id": "0"}
}
JSON
Response:
{
"type": "folder",
"id": "365037181307",
"name": "New Folder",
"created_at": "2026-02-08T14:56:17-08:00"
}
maton api -X PUT '/box/2.0/folders/{folder_id}' -H 'Content-Type: application/json' --input - <<'JSON'
{
"name": "Updated Folder Name",
"description": "Updated description"
}
JSON
maton api -X POST '/box/2.0/folders/{folder_id}/copy' -H 'Content-Type: application/json' --input - <<'JSON'
{
"name": "Copied Folder",
"parent": {"id": "0"}
}
JSON
maton api '/box/2.0/folders/{folder_id}' -X DELETE
Query parameters:
recursive - Set to true to delete non-empty foldersReturns 204 No Content on success.
maton api '/box/2.0/files/{file_id}'
maton api '/box/2.0/files/{file_id}/content'
Returns a redirect to the download URL.
Upload a new file (up to 50 MB for direct upload):
# maton api sends a body verbatim but does not build a multipart envelope:
# assemble it first, then hand the file to --input.
BOUNDARY="maton-$$"
{
printf -- '--%s\r\nContent-Disposition: form-data; name="attributes"\r\n\r\n{"name":"file.txt","parent":{"id":"0"}}\r\n' "$BOUNDARY"
printf -- '--%s\r\nContent-Disposition: form-data; name="file"; filename="binary data"\r\nContent-Type: application/octet-stream\r\n\r\n' "$BOUNDARY"
cat binary data
printf -- '\r\n'
printf -- '--%s--\r\n' "$BOUNDARY"
} > /tmp/upload.body
maton api -X POST '/box/api/2.0/files/content' \
-H "Content-Type: multipart/form-data; boundary=$BOUNDARY" \
--input /tmp/upload.body
The attributes field is a JSON string with:
name (required) - Filename to useparent.id (required) - Folder ID to upload to (use "0" for root)content_created_at - Optional timestampcontent_modified_at - Optional timestampResponse:
{
"total_count": 1,
"entries": [
{
"type": "file",
"id": "123456789",
"name": "file.txt",
"size": 1024,
"created_at": "2026-04-14T10:00:00-07:00",
"modified_at": "2026-04-14T10:00:00-07:00",
"parent": {"type": "folder", "id": "0", "name": "All Files"}
}
]
}
Note: Maton automatically routes upload endpoints to upload.box.com.
Upload a new version of an existing file:
# maton api sends a body verbatim but does not build a multipart envelope:
# assemble it first, then hand the file to --input.
BOUNDARY="maton-$$"
{
printf -- '--%s\r\nContent-Disposition: form-data; name="attributes"\r\n\r\n{"name":"file.txt"}\r\n' "$BOUNDARY"
printf -- '--%s\r\nContent-Disposition: form-data; name="file"; filename="binary data"\r\nContent-Type: application/octet-stream\r\n\r\n' "$BOUNDARY"
cat binary data
printf -- '\r\n'
printf -- '--%s--\r\n' "$BOUNDARY"
} > /tmp/upload.body
maton api -X POST '/box/api/2.0/files/{file_id}/content' \
-H "Content-Type: multipart/form-data; boundary=$BOUNDARY" \
--input /tmp/upload.body
For files larger than 50 MB (up to 50 GB), use chunked upload sessions. Maton automatically routes these endpoints to upload.box.com.
maton api -X POST '/box/api/2.0/files/upload_sessions' -H 'Content-Type: application/json' --input - <<'JSON'
{
"folder_id": "0",
"file_size": 104857600,
"file_name": "large_file.zip"
}
JSON
Response:
{
"id": "F971964745A5CD0C001BBE4E58196BFD",
"type": "upload_session",
"session_expires_at": "2026-04-15T10:00:00-07:00",
"part_size": 8388608,
"total_parts": 13,
"num_parts_processed": 0,
"session_endpoints": {
"list_parts": "https://upload.box.com/api/2.0/files/upload_sessions/F971964745A5CD0C001BBE4E58196BFD/parts",
"commit": "https://upload.box.com/api/2.0/files/upload_sessions/F971964745A5CD0C001BBE4E58196BFD/commit",
"upload_part": "https://upload.box.com/api/2.0/files/upload_sessions/F971964745A5CD0C001BBE4E58196BFD",
"status": "https://upload.box.com/api/2.0/files/upload_sessions/F971964745A5CD0C001BBE4E58196BFD",
"abort": "https://upload.box.com/api/2.0/files/upload_sessions/F971964745A5CD0C001BBE4E58196BFD"
}
}
maton api -X POST '/box/api/2.0/files/{file_id}/upload_sessions' -H 'Content-Type: application/json' --input - <<'JSON'
{
"file_size": 104857600,
"file_name": "large_file.zip"
}
JSON
maton api -X PUT '/box/api/2.0/files/upload_sessions/{session_id}' -H 'Content-Type: application/octet-stream' \
-H 'Content-Range: bytes 0-8388607/104857600' \
-H 'Digest: sha=<base64-encoded SHA-1 of part>' \
--input ./chunk.bin
Response:
{
"part": {
"part_id": "6F2D3A7B8C4E5F6A",
"offset": 0,
"size": 8388608,
"sha1": "134b65991ed521fcfe4724b7d814ab8ded5185dc"
}
}
maton api '/box/api/2.0/files/upload_sessions/{session_id}/parts'
After all parts are uploaded:
maton api -X POST '/box/api/2.0/files/upload_sessions/{session_id}/commit' -H 'Digest: sha=<base64-encoded SHA-1 of entire file>' -H 'Content-Type: application/json' --input - <<'JSON'
{
"parts": [
{"part_id": "6F2D3A7B8C4E5F6A", "offset": 0, "size": 8388608},
{"part_id": "7G3E4B8D9F5A6C7B", "offset": 8388608, "size": 8388608}
]
}
JSON
Response: Returns the created file object.
maton api '/box/api/2.0/files/upload_sessions/{session_id}' -X DELETE
Returns 204 No Content on success
maton api -X PUT '/box/2.0/files/{file_id}' -H 'Content-Type: application/json' --input - <<'JSON'
{
"name": "renamed-file.txt",
"description": "File description"
}
JSON
maton api -X POST '/box/2.0/files/{file_id}/copy' -H 'Content-Type: application/json' --input - <<'JSON'
{
"name": "copied-file.txt",
"parent": {"id": "0"}
}
JSON
maton api '/box/2.0/files/{file_id}' -X DELETE
Returns 204 No Content on success.
maton api '/box/2.0/files/{file_id}/versions'
Create a shared link by updating a file or folder:
maton api -X PUT '/box/2.0/folders/{folder_id}' -H 'Content-Type: application/json' --input - <<'JSON'
{
"shared_link": {
"access": "open"
}
}
JSON
Access levels:
open - Anyone with the linkcompany - Only users in the enterprisecollaborators - Only collaboratorsResponse includes:
{
"shared_link": {
"url": "https://app.box.com/s/sisarrztrenabyygfwqggbwommf8uucv",
"access": "open",
"effective_access": "open",
"is_password_enabled": false,
"permissions": {
"can_preview": true,
"can_download": true,
"can_edit": false
}
}
}
maton api '/box/2.0/folders/{folder_id}/collaborations'
maton api -X POST '/box/2.0/collaborations' -H 'Content-Type: application/json' --input - <<'JSON'
{
"item": {"type": "folder", "id": "365037181307"},
"accessible_by": {"type": "user", "login": "user@example.com"},
"role": "editor"
}
JSON
Roles: editor, viewer, previewer, uploader, previewer_uploader, viewer_uploader, co-owner
maton api -X PUT '/box/2.0/collaborations/{collaboration_id}' -H 'Content-Type: application/json' --input - <<'JSON'
{
"role": "viewer"
}
JSON
maton api '/box/2.0/collaborations/{collaboration_id}' -X DELETE
maton api '/box/2.0/search?query=document'
Query parameters:
query - Search query (required)type - Filter by type: file, folder, web_linkfile_extensions - Comma-separated extensionsancestor_folder_ids - Limit to specific folderslimit - Max results (default 30)offset - Pagination offsetResponse:
{
"total_count": 5,
"entries": [...],
"limit": 30,
"offset": 0,
"type": "search_results_items"
}
maton api '/box/2.0/events'
Query parameters:
stream_type - all, changes, sync, admin_logsstream_position - Position to start fromlimit - Max events to returnResponse:
{
"chunk_size": 4,
"next_stream_position": "30401068076164269",
"entries": [...]
}
maton api '/box/2.0/folders/trash/items'
maton api '/box/2.0/files/{file_id}/trash'
maton api '/box/2.0/folders/{folder_id}/trash'
maton api -X POST '/box/2.0/files/{file_id}'
maton api -X POST '/box/2.0/folders/{folder_id}'
maton api '/box/2.0/files/{file_id}/trash' -X DELETE
maton api '/box/2.0/folders/{folder_id}/trash' -X DELETE
maton api '/box/2.0/collections'
Response:
{
"total_count": 1,
"entries": [
{
"type": "collection",
"name": "Favorites",
"collection_type": "favorites",
"id": "35223030868"
}
]
}
maton api '/box/2.0/collections/{collection_id}/items'
maton api '/box/2.0/recent_items'
maton api '/box/2.0/webhooks'
maton api -X POST '/box/2.0/webhooks' -H 'Content-Type: application/json' --input - <<'JSON'
{
"target": {"id": "365037181307", "type": "folder"},
"address": "https://example.com/webhook",
"triggers": ["FILE.UPLOADED", "FILE.DOWNLOADED"]
}
JSON
Note: Webhook creation may require enterprise permissions.
maton api '/box/2.0/webhooks/{webhook_id}' -X DELETE
Box uses offset-based pagination:
maton api '/box/2.0/folders/0/items?limit=100&offset=0'
maton api '/box/2.0/folders/0/items?limit=100&offset=100'
Some endpoints use marker-based pagination with marker parameter.
Response:
{
"total_count": 250,
"entries": [...],
"offset": 0,
"limit": 100
}
0upload.box.comattributes JSON and file fieldsfields parameter to request specific fields and reduce response sizeIf-Match headerThe CLI above is this skill's documented path; the SDKs are an optional way to call the same gateway from application code. The two modes keep separate credential stores: the CLI uses the profile from maton login, while an SDK program signs in once with login(), which opens a browser and stores a session that Maton() reads. Box has no typed accessor yet, so calls go through the api passthrough, which takes the app and the path after it.
Python
pip install maton-ai
from maton_ai import Maton, login
# login()
maton = Maton()
# maton = Maton(api_key="...")
result = maton.api.get("box", "/2.0/users/me")
JavaScript
npm install @maton/sdk
import { Maton, login } from "@maton/sdk";
// await login()
const maton = new Maton();
// const maton = new Maton({ apiKey: "..." });
const result = await maton.api.get("box", "/2.0/users/me");
| Status | Meaning |
|---|---|
| 400 | Missing Box connection |
| 401 | Invalid, missing, or expired Maton credential |
| 429 | Rate limited (10 requests/second per account) |
| 500 | Internal Server Error |
| 4xx/5xx | Passthrough error from the Box API |
Errors from Box are passed through with their original status codes and response bodies.
maton whoami --json
"authenticated": false — login again with maton login --oauth."auth_type": "api_key" — prefer maton login --oauth so no long-lived key sits on the machine.maton whoami is the check.Then confirm the app is connected:
maton connection list box --status ACTIVE
Paths passed to maton api must start with /box/:
maton api '/box/2.0/users/me'maton api '/2.0/users/me'A 500 may mean the Box authorization expired. With the user's approval, create a new connection (maton connection create box) and complete authorization; once it is ACTIVE, delete the stale connection so the gateway uses the new one.
maton api.--paginate walks every page and -q/--jq trims the response before it reaches you. On typed commands, --jq requires --json.maton api; Host and Authorization are set by the gateway.Everything above uses the CLI, which holds the credential itself and never exposes it to the caller. Use the raw HTTP form below only where the CLI cannot be installed — a locked-down container, a CI step, a sandbox with no package manager. If maton is available, maton api does the same job without handling a secret.
Calling api.maton.ai directly means holding a long-lived Maton API key in the process environment, where it is readable by every child process and easy to leak into logs, crash dumps, shell history, and pasted output. Handle it accordingly:
[ -n "$MATON_API_KEY" ] && echo "MATON_API_KEY is set" || echo "MATON_API_KEY is not set"
.env, or a script makes it permanent. Let the environment that starts the session supply it — a CI secret store, a container secret, a secrets manager.ps output and shell history. Read it from the environment inside the process that makes the request, as below.api.maton.ai. It is not a credential for Box or any other third-party host.The request is a plain HTTPS call to host api.maton.ai at path /box/{native-api-path} with a bearer token; the gateway swaps in the connected app's credential. Add a Maton-Connection: {connection_id} header to pin a specific connection when the account has more than one. Query values must be URL-encoded. The Python standard library is enough — the key is read from the environment inside the process, so it never appears on a command line:
python3 - <<'PY'
import json, os, urllib.request
GATEWAY = "https://api.maton.ai"
req = urllib.request.Request(GATEWAY + "/box/2.0/users/me")
req.add_header("Authorization", "Bearer " + os.environ["MATON_API_KEY"])
req.add_header("User-Agent", "maton-box-skill/1.2")
# req.add_header("Maton-Connection", "{connection_id}")
with urllib.request.urlopen(req) as resp:
print(json.dumps(json.load(resp), indent=2))
PY
For a write, set method="POST" (or PUT/DELETE) on the Request, pass the JSON-encoded body as data=, and add a Content-Type: application/json header.
The same rules as the CLI apply to every request made this way: read-only calls first, and explicit user confirmation before any POST, PUT, PATCH, or DELETE.
The example prints the whole response body only to show the call working. Responses can carry personal data — names, email addresses, phone numbers, message and document contents — so extract just the fields the task needs instead of dumping the full payload, and do not write raw responses into logs, files, or anywhere the user has not asked for them.