Ticktick for AI agents
TickTick is a task manager and to-do list app across devices, used by individuals and small teams to organize projects, deadlines, and daily tasks in one list. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Ticktick.
Create a task in a project
Add a new task with a due date to a project list.
List all tasks
Pull the current task list across projects as a read-only status check.
Confirm before deleting a project
Check with the user before deleting a TickTick project, since its tasks go with it.
14 Ticktick actions, graded by risk.
Every Ticktick action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
5Look things up. Allowed by default.
- ticktick.list_all_tasksList All Tasks
- ticktick.get_user_projectGet User Projects
- ticktick.get_project_by_idGet Project By ID
- ticktick.get_project_with_dataGet project with data
- ticktick.get_task_by_project_and_idGet Task By Project And ID
write
7Create and change things. Allow, or ask the user first.
- ticktick.create_taskCreate Task
- ticktick.update_taskUpdate Task
- ticktick.create_task2Create Task (Deprecated)
- ticktick.create_projectCreate Project
- ticktick.update_projectUpdate Project
- ticktick.complete_taskComplete Task
- ticktick.oauth2_authorization_step1Generate OAuth2 Authorization URL
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- ticktick.delete_taskDelete Task
- ticktick.delete_projectDelete TickTick Project
Ticktick in three steps.
- 01Your users connect TicktickThey sign in to Ticktick on Arc0 Connect, under your brand, and approve the access you ask for.
- 02You set the rulesReads run, writes like “create Task” can wait for the user, and “delete Task” can be denied outright.
- 03Any agent can actYour agent calls Ticktick through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('ticktick', { read: 'allow', write: 'ask', // create_task destructive: 'deny', // delete_task }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Ticktick connects.
Users sign in to Ticktick on Arc0 Connect and approve the scopes you request. Build with Arc0’s Ticktick OAuth app, or bring your own so the Ticktick consent screen names you. Tokens refresh automatically, and you can export them whenever you want.
The same Ticktick connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- OAuth 2.0
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Ticktick from any agent.
Ticktick and Arc0, answered.
Can I use Ticktick with Claude, ChatGPT or Cursor?
Yes. Connect Ticktick to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Ticktick actions you allow.
How do users connect Ticktick?
Users sign in to Ticktick on Arc0 Connect and approve the scopes you request. Build with Arc0’s Ticktick OAuth app, or bring your own so the Ticktick consent screen names you. Tokens refresh automatically, and you can export them whenever you want.
Which Ticktick actions can my agent take?
14 in total: 5 read, 7 write and 2 destructive, such as “create Task”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Ticktick?
Yes. Actions like “delete Task” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Ticktick too?
Yes. The same Ticktick connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Ticktick into your agent.
Your users connect Ticktick once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan