Botsonic for AI agents
Botsonic is a no-code chatbot builder that businesses use to train bots on their own content and manage conversations, FAQs, and starter questions. 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 Botsonic.
Review a bot's conversations
Read-only pull of a bot's conversations and FAQs to check what visitors have been asking it.
Add a starter question
Create a new starter question for a bot after the user approves the wording.
Require approval before deleting a file
Flag deleting an uploaded file from a bot's knowledge source as destructive since it removes training data.
12 Botsonic actions, graded by risk.
Every Botsonic 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.
- botsonic.get_all_botsGet All Bots
- botsonic.get_all_faqsGet All FAQs
- botsonic.get_all_bot_dataGet All Bot Data
- botsonic.get_all_conversationsGet All Conversations
- botsonic.get_all_starter_presetsGet All Starter Presets
- botsonic.get_all_starter_questionsGet All Starter Questions
- botsonic.get_all_conversations_with_sourceGet All Conversations With Source
write
3Create and change things. Allow, or ask the user first.
- botsonic.create_starter_questionCreate Starter Question
- botsonic.update_starter_questionUpdate Starter Question
- botsonic.bulk_upload_urlsBulk Upload Bot URLs
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- botsonic.delete_uploaded_fileDelete Uploaded File
- botsonic.delete_starter_questionDelete Starter Question
Botsonic in three steps.
- 01Your users connect BotsonicThey add their Botsonic api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Starter Question” can wait for the user, and “delete Uploaded File” can be denied outright.
- 03Any agent can actYour agent calls Botsonic through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('botsonic', { read: 'allow', write: 'ask', // create_starter_question destructive: 'deny', // delete_uploaded_file }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Botsonic connects.
Users add their Botsonic 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 Botsonic 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 Botsonic from any agent.
Botsonic and Arc0, answered.
Can I use Botsonic with Claude, ChatGPT or Cursor?
Yes. Connect Botsonic 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 Botsonic actions you allow.
How do users connect Botsonic?
Users add their Botsonic 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 Botsonic actions can my agent take?
12 in total: 7 read, 3 write and 2 destructive, such as “create Starter Question”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Botsonic?
Yes. Actions like “delete Uploaded File” 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 Botsonic too?
Yes. The same Botsonic connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Botsonic into your agent.
Your users connect Botsonic 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