Bonsai for AI agents
Bonsai is a managed Elasticsearch and OpenSearch hosting service that engineering teams use to run and monitor search clusters without managing the underlying infrastructure themselves. 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 Bonsai.
Check a cluster's health
Read-only lookup of a Bonsai Elasticsearch or OpenSearch cluster's details before making any changes to it.
List provisioned spaces
Retrieve the list of spaces on the account to see which search clusters currently exist.
Review a space before scaling
Pull a specific space's details so the user can decide whether to resize or reconfigure it.
3 Bonsai actions, graded by risk.
Every Bonsai action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- bonsai.list_spacesList Spaces
- bonsai.get_space_detailsRetrieve Space Details
- bonsai.get_cluster_detailsGet Bonsai Cluster Details
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.
Bonsai in three steps.
- 01Your users connect BonsaiThey add their Bonsai username and password 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 Bonsai through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('bonsai', { 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 Bonsai connects.
Users add their Bonsai username and password 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 Bonsai 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
- Username and password
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Bonsai from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraphMore databases and spreadsheets apps.
Bonsai and Arc0, answered.
Can I use Bonsai with Claude, ChatGPT or Cursor?
Yes. Connect Bonsai 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 Bonsai actions you allow.
How do users connect Bonsai?
Users add their Bonsai username and password 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 Bonsai actions can my agent take?
3 in total: 3 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Bonsai?
Yes. Allow read actions and deny writes in the Bonsai policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Bonsai too?
Yes. The same Bonsai connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Bonsai into your agent.
Your users connect Bonsai once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan