Mindbody for AI agents
Mindbody is scheduling and business management software for fitness, wellness, and beauty studios to run classes, manage clients, and process payments. 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 Mindbody.
Check class availability
Look up open spots in an upcoming class before booking a client into it.
Add a client to a class
Book a client into a class once a session time is confirmed.
Approve before removing a client
Require approval before removing a client from a class, since it affects their booking and any cancellation policy.
14 Mindbody actions, graded by risk.
Every Mindbody action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
11Look things up. Allowed by default.
- mindbody.list_staffList Staff
- mindbody.find_clientsFind Clients
- mindbody.list_classesList Classes
- mindbody.list_locationsList Locations
- mindbody.search_productsSearch Products
- mindbody.list_enrollmentsList Enrollments
- mindbody.list_session_typesList Session Types
- mindbody.list_accessible_sitesList Accessible Sites
- mindbody.get_client_complete_infoGet Client Complete Info
- mindbody.list_active_session_timesList Active Session Times
- mindbody.get_appointment_availabilityGet Appointment Availability
write
2Create and change things. Allow, or ask the user first.
- mindbody.create_clientCreate Client
- mindbody.add_client_to_classAdd Client to Class
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- mindbody.remove_client_from_classRemove Client From Class
Mindbody in three steps.
- 01Your users connect MindbodyThey add their Mindbody api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Client” can wait for the user, and “remove Client From Class” can be denied outright.
- 03Any agent can actYour agent calls Mindbody through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('mindbody', { read: 'allow', write: 'ask', // create_client destructive: 'deny', // remove_client_from_class }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Mindbody connects.
Users add their Mindbody 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 Mindbody 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 Mindbody from any agent.
Mindbody and Arc0, answered.
Can I use Mindbody with Claude, ChatGPT or Cursor?
Yes. Connect Mindbody 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 Mindbody actions you allow.
How do users connect Mindbody?
Users add their Mindbody 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 Mindbody actions can my agent take?
14 in total: 11 read, 2 write and 1 destructive, such as “create Client”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Mindbody?
Yes. Actions like “remove Client From Class” 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 Mindbody too?
Yes. The same Mindbody connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Mindbody into your agent.
Your users connect Mindbody once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan