Extrovert for AI agents
Extrovert automates LinkedIn prospect engagement, running campaigns with defined writing styles and monitored topics for outreach teams that want a consistent brand voice at scale. 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 Extrovert.
Look up a LinkedIn prospect
Find a prospect by their LinkedIn URL to check their details before adding them to a campaign.
Check a campaign's progress
Get a campaign's status to see how outreach is progressing for a target list.
Confirm before deleting a writing style
Require approval before deleting a writing style, since active campaigns may still reference it.
15 Extrovert actions, graded by risk.
Every Extrovert action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
9Look things up. Allowed by default.
- extrovert.list_stylesList Styles
- extrovert.get_campaignGet Campaign
- extrovert.get_prospectGet Prospect
- extrovert.list_contextsList Contexts
- extrovert.list_campaignsList Campaigns
- extrovert.list_prospectsList Prospects
- extrovert.list_team_membersList Team Members
- extrovert.get_workspace_plan_featuresGet Workspace Plan Features
- extrovert.find_prospect_by_linkedin_urlFind Prospect by LinkedIn URL
write
4Create and change things. Allow, or ask the user first.
- extrovert.create_styleCreate Style
- extrovert.update_styleUpdate Style
- extrovert.create_contextCreate Context
- extrovert.update_contextUpdate Context
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- extrovert.delete_styleDelete Style
- extrovert.delete_contextDelete Context
Extrovert in three steps.
- 01Your users connect ExtrovertThey add their Extrovert api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Style” can wait for the user, and “delete Style” can be denied outright.
- 03Any agent can actYour agent calls Extrovert through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('extrovert', { read: 'allow', write: 'ask', // create_style destructive: 'deny', // delete_style }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Extrovert connects.
Users add their Extrovert 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 Extrovert 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 Extrovert from any agent.
Extrovert and Arc0, answered.
Can I use Extrovert with Claude, ChatGPT or Cursor?
Yes. Connect Extrovert 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 Extrovert actions you allow.
How do users connect Extrovert?
Users add their Extrovert 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 Extrovert actions can my agent take?
15 in total: 9 read, 4 write and 2 destructive, such as “create Style”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Extrovert?
Yes. Actions like “delete Style” 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 Extrovert too?
Yes. The same Extrovert connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Extrovert into your agent.
Your users connect Extrovert 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