Contacts+ for AI agents
Contacts+ manages personal contact and tag data, giving people a synced address book they can search and organize across their accounts. 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 Contacts+.
Search for a contact
Search contacts by name or company before adding a new interaction to their record.
Add a tag to a contact
Update a contact's tags to keep them organized under the right group.
Confirm before deleting a contact
Confirm before deleting a contact, since their tags and details are removed permanently.
13 Contacts+ actions, graded by risk.
Every Contacts+ 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.
- contacts.get_tagsGet Tags
- contacts.list_tagsList Tags
- contacts.get_accountGet Account
- contacts.get_contactsGet Contacts
- contacts.list_contactsList Contacts
- contacts.search_contactsSearch Contacts
write
5Create and change things. Allow, or ask the user first.
- contacts.create_tagCreate Tag
- contacts.update_tagUpdate Tag
- contacts.create_contactCreate Contact
- contacts.update_contactUpdate Contact
- contacts.update_contact_tagsUpdate Contact Tags
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- contacts.delete_tagDelete Tag
- contacts.delete_contactDelete Contact
Contacts+ in three steps.
- 01Your users connect Contacts+They sign in to Contacts+ on Arc0 Connect, under your brand, and approve the access you ask for.
- 02You set the rulesReads run, writes like “create Tag” can wait for the user, and “delete Tag” can be denied outright.
- 03Any agent can actYour agent calls Contacts+ through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('contacts', { read: 'allow', write: 'ask', // create_tag destructive: 'deny', // delete_tag }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Contacts+ connects.
Users sign in to Contacts+ on Arc0 Connect and approve the scopes you request. Build with Arc0’s Contacts+ OAuth app, or bring your own so the Contacts+ consent screen names you. Tokens refresh automatically, and you can export them whenever you want.
The same Contacts+ 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 Contacts+ from any agent.
Contacts+ and Arc0, answered.
Can I use Contacts+ with Claude, ChatGPT or Cursor?
Yes. Connect Contacts+ 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 Contacts+ actions you allow.
How do users connect Contacts+?
Users sign in to Contacts+ on Arc0 Connect and approve the scopes you request. Build with Arc0’s Contacts+ OAuth app, or bring your own so the Contacts+ consent screen names you. Tokens refresh automatically, and you can export them whenever you want.
Which Contacts+ actions can my agent take?
13 in total: 6 read, 5 write and 2 destructive, such as “create Tag”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Contacts+?
Yes. Actions like “delete Tag” 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 Contacts+ too?
Yes. The same Contacts+ connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Contacts+ into your agent.
Your users connect Contacts+ once, under your brand. Your agent gets 13 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan