Odel
orita mcp

orita mcp

Local
@alkilo-doPythonMITUpdated 1mo ago

Provider resolution for AI apps — search, rank, hold, confirm bookings across your provider network.

orita-mcp

MCP server for the Orita Provider Resolution API — lets AI agents search a provider network, apply eligibility rules, resolve availability, and safely confirm bookings.

PyPI MCP Registry License: MIT

What this does

Orita resolves the provider-routing problem:

Your application knows what service the customer needs, but not which professional is eligible and available.

This MCP server exposes that resolution workflow as tools that AI agents (Claude, Cursor, and compatible clients) can call natively.

Primary workflow

resolve_scheduling          → search provider network, return ranked options
hold_scheduling_option      → temporarily reserve the selected slot
confirm_scheduling_resolution → confirm booking after customer approval

Tools

ToolDescriptionModifies state?
resolve_schedulingSearch provider network, apply eligibility rules, return ranked explained optionsNo
get_resolutionRetrieve resolution with options, exclusions, and expiryNo
hold_scheduling_optionTemporarily hold a slot (2 min default, 10 min max)Application-defined
release_scheduling_optionRelease a held slotYes
confirm_scheduling_resolutionCreate the booking after customer approvalYes — requires approval
reschedule_bookingMove to a new approved slotYes — requires approval
cancel_bookingCancel a bookingYes — requires approval
get_bookingRetrieve booking detailsNo
list_professionalsList providers in the networkNo
get_slotsGet slots for a known providerNo

Agent safety

✓ resolve_scheduling, get_resolution, list_professionals, get_slots
  → No customer approval required

⚠ hold_scheduling_option
  → Application-defined

✗ confirm_scheduling_resolution, reschedule_booking, cancel_booking
  → Require explicit customer approval before calling
  → Display provider, service, time, timezone, and cancellation policy first

Never call confirm_scheduling_resolution until the customer has explicitly approved:

  • Provider name
  • Service
  • Date and time
  • Timezone
  • Cancellation policy

Connect via remote server

{
  "mcpServers": {
    "orita": {
      "url": "https://orita.online/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_ORITA_API_KEY"
      }
    }
  }
}

Note: Requests must include Accept: application/json, text/event-stream. MCP-compatible clients send this automatically.

Install via PyPI

pip install orita-mcp
ORITA_API_KEY=orita_... python -m orita_mcp

Get an API key

Free at orita.online/sign-up — no credit card. 50 active providers, 5,000 resolutions/month included on the free plan.

Resources