Botdog for AI agents
Botdog is a LinkedIn outreach platform that sales teams use to run campaigns, manage leads, and send or schedule connection and follow-up messages. 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 Botdog.
Check campaign performance
Read-only lookup of campaign statistics and daily analytics before adjusting an outreach sequence.
Add leads to a campaign
Add a batch of leads to an existing LinkedIn campaign after the user approves the list.
Require approval before sending a message
Treat sending or scheduling a LinkedIn message to a lead as needing the user's sign-off on the wording.
12 Botdog actions, graded by risk.
Every Botdog action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
10Look things up. Allowed by default.
- botdog.list_leadsList Leads
- botdog.list_usersList Team Users
- botdog.get_campaignGet Campaign
- botdog.get_analyticsGet Analytics
- botdog.list_accountsList LinkedIn Accounts
- botdog.list_campaignsList Campaigns
- botdog.get_current_teamGet Current Team
- botdog.get_daily_analyticsGet Daily Analytics
- botdog.get_campaign_sequenceGet Campaign Sequence
- botdog.get_campaign_statisticsGet Campaign Statistics
write
2Create and change things. Allow, or ask the user first.
- botdog.send_messageSend or Schedule Message
- botdog.add_leads_to_campaignAdd Leads to Campaign
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Botdog in three steps.
- 01Your users connect BotdogThey add their Botdog api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “send or Schedule Message” can wait for the user to approve.
- 03Any agent can actYour agent calls Botdog through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('botdog', { read: 'allow', write: 'ask', // send_message destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Botdog connects.
Users add their Botdog 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 Botdog 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 Botdog from any agent.
Botdog and Arc0, answered.
Can I use Botdog with Claude, ChatGPT or Cursor?
Yes. Connect Botdog 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 Botdog actions you allow.
How do users connect Botdog?
Users add their Botdog 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 Botdog actions can my agent take?
12 in total: 10 read, 2 write and 0 destructive, such as “send or Schedule Message”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Botdog?
Yes. Allow read actions and deny writes in the Botdog policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Botdog too?
Yes. The same Botdog connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Botdog into your agent.
Your users connect Botdog once, under your brand. Your agent gets 12 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan