Sitespeakai for AI agents
SiteSpeakAI turns a company's own content into a custom-trained chatbot that answers customer questions on its website, cutting down repetitive support tickets. 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 Sitespeakai.
Review leads captured by the chatbot
Pull the leads a chatbot collected from website visitors so sales can follow up without checking the dashboard.
List active chatbots on the account
List the chatbots configured for a business as a read-only check before making changes to any of them.
Check a chatbot's smart prompts
Retrieve the smart prompts configured for a chatbot to confirm which suggested questions visitors currently see.
4 Sitespeakai actions, graded by risk.
Every Sitespeakai action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- sitespeakai.get_userGet Authenticated User
- sitespeakai.get_leadsGet Leads
- sitespeakai.get_promptsGet Smart Prompts
- sitespeakai.list_chatbotsList Chatbots
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Sitespeakai in three steps.
- 01Your users connect SitespeakaiThey add their Sitespeakai api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Sitespeakai through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('sitespeakai', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Sitespeakai connects.
Users add their Sitespeakai 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 Sitespeakai 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 Sitespeakai from any agent.
Sitespeakai and Arc0, answered.
Can I use Sitespeakai with Claude, ChatGPT or Cursor?
Yes. Connect Sitespeakai 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 Sitespeakai actions you allow.
How do users connect Sitespeakai?
Users add their Sitespeakai 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 Sitespeakai actions can my agent take?
4 in total: 4 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Sitespeakai?
Yes. Allow read actions and deny writes in the Sitespeakai policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Sitespeakai too?
Yes. The same Sitespeakai connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Sitespeakai into your agent.
Your users connect Sitespeakai once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan