Autobound for AI agents
Autobound generates personalized sales outreach content and account insights from signals like funding and job changes, used by sales reps to write emails that reference real context. 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 Autobound.
Research a target account
Generate insights on a prospect, like recent funding or leadership changes, before a rep drafts an outreach message.
Draft a personalized cold email
Generate a personalized outreach email for a specific contact and save it as a draft for the rep to review and send.
Hold a draft for rep approval
Generate personalized talking points for a call and hold the draft for the rep's approval before it goes out.
2 Autobound actions, graded by risk.
Every Autobound action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
0Look things up. Allowed by default.
- No read actions.
write
2Create and change things. Allow, or ask the user first.
- autobound.generate_insightsGenerate Insights
- autobound.generate_personalized_contentGenerate Personalized Content
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Autobound in three steps.
- 01Your users connect AutoboundThey add their Autobound api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “generate Insights” can wait for the user to approve.
- 03Any agent can actYour agent calls Autobound through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('autobound', { read: 'allow', write: 'ask', // generate_insights destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Autobound connects.
Users add their Autobound 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 Autobound 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 Autobound from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Autobound and Arc0, answered.
Can I use Autobound with Claude, ChatGPT or Cursor?
Yes. Connect Autobound 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 Autobound actions you allow.
How do users connect Autobound?
Users add their Autobound 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 Autobound actions can my agent take?
2 in total: 0 read, 2 write and 0 destructive, such as “generate Insights”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Autobound?
Yes. Allow read actions and deny writes in the Autobound policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Autobound too?
Yes. The same Autobound connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Autobound into your agent.
Your users connect Autobound once, under your brand. Your agent gets 2 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan