Install
openclaw skills install @byungkyu/sunsamaSunsama MCP integration with managed authentication. Manage daily tasks, calendar events, backlog, objectives, time tracking, and email threads from connected accounts (Gmail, Outlook). Use this skill when users want to interact with Sunsama for task management, daily planning, etc.
openclaw skills install @byungkyu/sunsamaAccess Sunsama via MCP (Model Context Protocol) with managed authentication.
All access runs through the Maton gateway and the maton CLI.
maton login --oauth # authenticate once (OAuth, recommended)
maton connection create sunsama --method MCP # connect the account (needs user approval)
maton api -X POST '/sunsama/search_tasks' -H 'Content-Type: application/json' --input - <<'JSON'
{"searchTerm": "meeting"}
JSON # 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 sunsama --method MCP --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": "sunsama",
"method": "MCP",
"metadata": {}
}
]
}
Refer to maton connection list --help for possible flags and values.
Requires explicit user approval. Confirm that the user intends to authorize Sunsama MCP access before running this. Never create a connection on your own initiative.
maton connection create sunsama --method MCP
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": "sunsama",
"metadata": {}
}
}
Open the returned URL in a browser to complete authorizing Sunsama MCP. If Sunsama MCP 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.
sunsama can hold an OAUTH2 connection as well as an MCP one. Routing an MCP tool call to the OAUTH2 connection fails with Connection ... is not an MCP connection, so pin the MCP connection explicitly:
maton api -X POST '/sunsama/search_tasks' --connection {connection_id} -H 'Content-Type: application/json' --input - <<'JSON'
{"searchTerm": "meeting"}
JSON
Sunsama MCP has no typed maton sunsama commands yet, so every call goes through maton api.
maton api -X POST '/sunsama/search_tasks' -H 'Content-Type: application/json' --input - <<'JSON'
{"searchTerm": "meeting"}
JSON
Paths are /sunsama/{native-api-path}. The gateway forwards everything after the app segment to MCP server 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 '/sunsama/{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 Sunsama's MCP server and automatically injects your credentials. The {tool-name} corresponds to the MCP tool name (e.g., search_tasks).
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 sunsama --method MCP. 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.All MCP tools use POST method:
| Tool | Description | Schema |
|---|---|---|
search_tasks | Search tasks by term | schema |
create_task | Create a new task | schema |
edit_task_title | Update task title | schema |
delete_task | Delete a task | schema |
mark_task_as_completed | Mark task complete | schema |
mark_task_as_incomplete | Mark task incomplete | schema |
append_task_notes | Add notes to task | schema |
edit_task_time_estimate | Set time estimate | schema |
edit_task_recurrence_rule | Set recurrence | schema |
get_task_time_estimate | Get AI time estimate | schema |
restore_task | Restore deleted task | schema |
| Tool | Description | Schema |
|---|---|---|
add_subtasks_to_task | Add subtasks | schema |
edit_subtask_title | Update subtask title | schema |
mark_subtask_as_completed | Mark subtask complete | schema |
mark_subtask_as_incomplete | Mark subtask incomplete | schema |
| Tool | Description | Schema |
|---|---|---|
get_backlog_tasks | List backlog tasks | schema |
move_task_to_backlog | Move task to backlog | schema |
move_task_from_backlog | Move from backlog to day | schema |
reposition_task_in_backlog | Reorder backlog task | schema |
change_backlog_folder | Change task folder | schema |
create_braindump_task | Create backlog task | schema |
| Tool | Description | Schema |
|---|---|---|
move_task_to_day | Reschedule task | schema |
reorder_tasks | Reorder day's tasks | schema |
timebox_a_task_to_calendar | Block time for task | schema |
set_shutdown_time | Set daily end time | schema |
| Tool | Description | Schema |
|---|---|---|
create_calendar_event | Create calendar event | schema |
delete_calendar_event | Delete calendar event | schema |
move_calendar_event | Reschedule event | schema |
import_task_from_calendar_event | Import event as task | schema |
set_calendar_event_allow_task_projections | Toggle task overlap | schema |
accept_meeting_invite | Accept meeting | schema |
decline_meeting_invite | Decline meeting | schema |
| Tool | Description | Schema |
|---|---|---|
start_task_timer | Start timer | schema |
stop_task_timer | Stop timer | schema |
| Tool | Description | Schema |
|---|---|---|
create_channel | Create channel/context | schema |
add_task_to_channel | Assign task to channel | schema |
create_weekly_objective | Create weekly goal | schema |
align_task_with_objective | Link task to objective | schema |
| Tool | Description | Schema |
|---|---|---|
get_archived_tasks | List archived tasks | schema |
unarchive_task | Restore archived task | schema |
| Tool | Description | Schema |
|---|---|---|
list_email_threads | List email threads | schema |
create_follow_up_task_from_email | Create task from email | schema |
delete_email_thread | Delete email thread | schema |
mark_email_thread_as_read | Mark email as read | schema |
| Tool | Description | Schema |
|---|---|---|
delete_all_incomplete_recurring_task_instances | Delete future recurrences | schema |
update_all_incomplete_recurring_task_instances | Update future recurrences | schema |
| Tool | Description | Schema |
|---|---|---|
toggle_auto_import_events | Toggle event auto-import | schema |
update_calendar_preferences | Update calendar settings | schema |
update_import_event_filters | Set event filters | schema |
log_user_feedback | Submit feedback | schema |
Search for tasks by keyword:
maton api -X POST '/sunsama/search_tasks' -H 'Content-Type: application/json' --input - <<'JSON'
{
"searchTerm": "meeting"
}
JSON
Response:
{
"content": [
{
"type": "text",
"text": "{\"tasks\":[{\"_id\":\"69a6bf3a04d3cd0001595308\",\"title\":\"Team meeting prep\",\"scheduledDate\":\"2026-03-03\",\"completed\":false}]}"
}
],
"isError": false
}
Create a new task scheduled for a specific day:
maton api -X POST '/sunsama/create_task' -H 'Content-Type: application/json' --input - <<'JSON'
{
"title": "Review quarterly report",
"day": "2026-03-03",
"alreadyInTaskList": false
}
JSON
Response:
{
"content": [
{
"type": "text",
"text": "{\"success\":true,\"task\":{\"_id\":\"69a6bf3a04d3cd0001595308\",\"title\":\"Review quarterly report\",\"notes\":\"\",\"timeEstimate\":\"20 minutes\",\"sortOrder\":-1772535610535,\"isPersonal\":false,\"isWork\":true,\"isPrivate\":false,\"isArchived\":false,\"completed\":false,\"isBacklogged\":false,\"scheduledDate\":\"2026-03-03\",\"subtasks\":[],\"channel\":\"work\",\"folder\":null,\"timeboxEventIds\":[]}}"
}
],
"isError": false
}
List all tasks in the backlog:
maton api -X POST '/sunsama/get_backlog_tasks' -H 'Content-Type: application/json' --input - <<'JSON'
{}
JSON
Response:
{
"content": [
{
"type": "text",
"text": "{\"tasks\":[],\"queryId\":\"bb7d004a-0b29-49d9-8345-6d9037786fbb\",\"totalPages\":1}"
}
],
"isError": false
}
maton api -X POST '/sunsama/mark_task_as_completed' -H 'Content-Type: application/json' --input - <<'JSON'
{
"taskId": "69a6bf3a04d3cd0001595308",
"finishedDay": "2026-03-03"
}
JSON
maton api -X POST '/sunsama/add_subtasks_to_task' -H 'Content-Type: application/json' --input - <<'JSON'
{
"taskId": "69a6bf3a04d3cd0001595308",
"subtasks": [
{"title": "Step 1: Research"},
{"title": "Step 2: Draft outline"},
{"title": "Step 3: Review"}
]
}
JSON
maton api -X POST '/sunsama/create_calendar_event' -H 'Content-Type: application/json' --input - <<'JSON'
{
"title": "Team standup",
"startDate": "2026-03-03T09:00:00"
}
JSON
Reschedule a task to a different day:
maton api -X POST '/sunsama/move_task_to_day' -H 'Content-Type: application/json' --input - <<'JSON'
{
"taskId": "69a6bf3a04d3cd0001595308",
"calendarDay": "2026-03-04"
}
JSON
Block time for a task on your calendar:
maton api -X POST '/sunsama/timebox_a_task_to_calendar' -H 'Content-Type: application/json' --input - <<'JSON'
{
"taskId": "69a6bf3a04d3cd0001595308",
"startDate": "2026-03-03",
"startTime": "14:00"
}
JSON
maton api -X POST '/sunsama/create_weekly_objective' -H 'Content-Type: application/json' --input - <<'JSON'
{
"title": "Complete Q1 planning",
"weekStartDay": "2026-03-03"
}
JSON
Create a backlog task with a time bucket:
maton api -X POST '/sunsama/create_braindump_task' -H 'Content-Type: application/json' --input - <<'JSON'
{
"title": "Research new tools",
"timeBucket": "in the next month"
}
JSON
Time bucket options:
"in the next two weeks""in the next month""in the next quarter""in the next year""someday""never"maton api -X POST '/sunsama/start_task_timer' -H 'Content-Type: application/json' --input - <<'JSON'
{
"taskId": "69a6bf3a04d3cd0001595308"
}
JSON
maton api -X POST '/sunsama/stop_task_timer' -H 'Content-Type: application/json' --input - <<'JSON'
{
"taskId": "69a6bf3a04d3cd0001595308"
}
JSON
Set when your workday ends:
maton api -X POST '/sunsama/set_shutdown_time' -H 'Content-Type: application/json' --input - <<'JSON'
{
"calendarDay": "2026-03-03",
"hour": 18,
"minute": 0
}
JSON
YYYY-MM-DD for days, ISO 8601 for datetimes{"content": [{"type": "text", "text": "..."}], "isError": false} formattext field contains JSON-stringified data that should be parsedThe 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. Sunsama MCP 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.post("sunsama", "/search_tasks", json={"searchTerm": "meeting"})
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.post("sunsama", "/search_tasks", { json: {"searchTerm": "meeting"} });
| Status | Meaning |
|---|---|
| 400 | Missing Sunsama MCP 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 Sunsama MCP API |
Errors from Sunsama MCP 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 sunsama --status ACTIVE
Connection ... is not an MCP connection means the request was routed to an OAUTH2 connection
for sunsama. List the MCP ones and pin the right connection:
maton connection list sunsama --method MCP --status ACTIVE
If none exists, create one with the user's approval: maton connection create sunsama --method MCP.
Paths passed to maton api must start with /sunsama/:
maton api '/sunsama/search_tasks'maton api '/search_tasks'A 500 may mean the Sunsama MCP authorization expired. With the user's approval, create a new connection (maton connection create sunsama) 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 Sunsama MCP or any other third-party host.The request is a plain HTTPS call to host api.maton.ai at path /sunsama/{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"
body = json.dumps({"searchTerm": "meeting"}).encode()
req = urllib.request.Request(GATEWAY + "/sunsama/search_tasks", data=body, method="POST")
req.add_header("Content-Type", "application/json")
req.add_header("Authorization", "Bearer " + os.environ["MATON_API_KEY"])
req.add_header("User-Agent", "maton-sunsama-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 read-only call, drop data= and method= and the Content-Type header; for PUT/DELETE, change method= accordingly.
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.