AimTell for AI agents
AimTell is a web push notification platform for engaging site visitors with targeted campaigns. Marketers use it to segment subscribers and track delivery performance. 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 AimTell.
List active subscribers
Pull the current list of push notification subscribers for a website before targeting a new campaign.
Send a push notification
Push a notification out to a segment of subscribers, a write action worth reviewing before it sends.
Delete a segment
Remove a subscriber segment from the account, a destructive action that should be confirmed before it happens.
15 AimTell actions, graded by risk.
Every AimTell action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
7Look things up. Allowed by default.
- aimtell.list_segmentsList Segments
- aimtell.list_websitesList Websites
- aimtell.list_campaignsList Campaigns
- aimtell.list_subscribersList Subscribers
- aimtell.get_campaign_resultsGet Campaign Results
- aimtell.list_notification_logsList Notification Logs
- aimtell.get_analytics_over_timeGet Analytics Over Time
write
6Create and change things. Allow, or ask the user first.
- aimtell.create_segmentCreate Segment
- aimtell.update_segmentUpdate Segment
- aimtell.create_manual_campaignCreate Manual Campaign
- aimtell.send_push_notificationSend Push Notification
- aimtell.update_manual_campaignUpdate Manual Campaign
- aimtell.set_subscriber_attributesSet Subscriber Attributes
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- aimtell.delete_segmentDelete Segment
- aimtell.delete_manual_campaignDelete Manual Campaign
AimTell in three steps.
- 01Your users connect AimTellThey add their AimTell api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Segment” can wait for the user, and “delete Segment” can be denied outright.
- 03Any agent can actYour agent calls AimTell through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('aimtell', { read: 'allow', write: 'ask', // create_segment destructive: 'deny', // delete_segment }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How AimTell connects.
Users add their AimTell api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same AimTell 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
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use AimTell from any agent.
AimTell and Arc0, answered.
Can I use AimTell with Claude, ChatGPT or Cursor?
Yes. Connect AimTell 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 AimTell actions you allow.
How do users connect AimTell?
Users add their AimTell api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which AimTell actions can my agent take?
15 in total: 7 read, 6 write and 2 destructive, such as “create Segment”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in AimTell?
Yes. Actions like “delete Segment” 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 AimTell too?
Yes. The same AimTell connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug AimTell into your agent.
Your users connect AimTell once, under your brand. Your agent gets 15 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan