ManyReach for AI agents
ManyReach is a cold email outreach platform for running campaigns, managing prospect lists, and tracking sender performance across multiple mailboxes. 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 ManyReach.
Add a prospect to a campaign
Create a new prospect and add them to an active outreach campaign.
Check a campaign's messages
List messages sent under a campaign to review reply activity and gauge how prospects are responding.
Approve before deleting a resource
Require approval before deleting a campaign or list, since it removes its outreach history.
16 ManyReach actions, graded by risk.
Every ManyReach 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.
- manyreach.list_tagsList Tags
- manyreach.list_listsList Mailing Lists
- manyreach.list_sendersList Senders
- manyreach.list_messagesList Messages
- manyreach.list_campaignsList Campaigns
- manyreach.list_prospectsList Prospects
- manyreach.get_account_overviewGet Account Overview
write
8Create and change things. Allow, or ask the user first.
- manyreach.create_tagCreate Tag
- manyreach.update_tagUpdate Tag
- manyreach.create_listCreate Mailing List
- manyreach.update_listUpdate Mailing List
- manyreach.create_campaignCreate Campaign
- manyreach.create_prospectCreate Prospect
- manyreach.update_campaignUpdate Campaign
- manyreach.update_prospectUpdate Prospect
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- manyreach.delete_outreach_resourceDelete Outreach Resource
ManyReach in three steps.
- 01Your users connect ManyReachThey add their ManyReach api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Tag” can wait for the user, and “delete Outreach Resource” can be denied outright.
- 03Any agent can actYour agent calls ManyReach through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('manyreach', { read: 'allow', write: 'ask', // create_tag destructive: 'deny', // delete_outreach_resource }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How ManyReach connects.
Users add their ManyReach 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 ManyReach 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 ManyReach from any agent.
ManyReach and Arc0, answered.
Can I use ManyReach with Claude, ChatGPT or Cursor?
Yes. Connect ManyReach 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 ManyReach actions you allow.
How do users connect ManyReach?
Users add their ManyReach 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 ManyReach actions can my agent take?
16 in total: 7 read, 8 write and 1 destructive, such as “create Tag”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in ManyReach?
Yes. Actions like “delete Outreach Resource” 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 ManyReach too?
Yes. The same ManyReach connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug ManyReach into your agent.
Your users connect ManyReach once, under your brand. Your agent gets 16 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan