MailBluster for AI agents
MailBluster is an email marketing platform for sending personalized promotional campaigns to large subscriber lists at low cost compared to bigger competitors. 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 MailBluster.
Add a new lead
Create a new lead in MailBluster after a signup form is submitted elsewhere.
Look up a lead's details
Pull a lead's record to check their fields and current status before deciding how to follow up.
Approve before deleting a lead
Require approval before deleting a lead, since it removes their record permanently.
15 MailBluster actions, graded by risk.
Every MailBluster action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- mailbluster.get_leadGet Lead
- mailbluster.get_orderGet Order
- mailbluster.get_productGet Product
- mailbluster.list_fieldsList Fields
- mailbluster.list_ordersList Orders
- mailbluster.list_productsList Products
write
6Create and change things. Allow, or ask the user first.
- mailbluster.create_leadCreate MailBluster Lead
- mailbluster.update_leadUpdate MailBluster Lead
- mailbluster.create_orderCreate Order
- mailbluster.update_orderUpdate Order
- mailbluster.create_productCreate Product
- mailbluster.update_productMailBluster Update Product
destructive
3Delete, cancel or archive. Ask first, or deny outright.
- mailbluster.delete_leadDelete MailBluster Lead
- mailbluster.delete_orderDelete Order
- mailbluster.delete_productDelete Mailbluster Product
MailBluster in three steps.
- 01Your users connect MailBlusterThey add their MailBluster api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create MailBluster Lead” can wait for the user, and “delete MailBluster Lead” can be denied outright.
- 03Any agent can actYour agent calls MailBluster through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('mailbluster', { read: 'allow', write: 'ask', // create_lead destructive: 'deny', // delete_lead }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How MailBluster connects.
Users add their MailBluster 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 MailBluster 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 MailBluster from any agent.
MailBluster and Arc0, answered.
Can I use MailBluster with Claude, ChatGPT or Cursor?
Yes. Connect MailBluster 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 MailBluster actions you allow.
How do users connect MailBluster?
Users add their MailBluster 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 MailBluster actions can my agent take?
15 in total: 6 read, 6 write and 3 destructive, such as “create MailBluster Lead”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in MailBluster?
Yes. Actions like “delete MailBluster Lead” 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 MailBluster too?
Yes. The same MailBluster connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug MailBluster into your agent.
Your users connect MailBluster 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