About orita-provider-resolution
orita-provider-resolution is an MCP server for routing service requests to eligible, available professionals. It ranks provider options, supports temporary slot holds, and requires customer approval for booking changes and cancellations.
Key features
- 01Search and rank eligible providers
- 02Retrieve resolution details and exclusions
- 03Temporarily hold or release a slot
- 04Confirm, reschedule, or cancel bookings
- 05List professionals and provider slots
Use cases
- 01Find eligible professionals for a service request
- 02Hold an appointment while awaiting customer approval
- 03Book or change an approved appointment
MCP support
Exposes the Orita Provider Resolution API workflow as tools for MCP clients, including provider search, slot holds, and booking management. Booking confirmation, rescheduling, and cancellation require explicit customer approval.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx orita-mcpORITA_API_KEYSecretOrita API key — get one at orita.online/settingsLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEorita-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.
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
| Tool | Description | Modifies state? |
|---|---|---|
resolve_scheduling | Search provider network, apply eligibility rules, return ranked explained options | No |
get_resolution | Retrieve resolution with options, exclusions, and expiry | No |
hold_scheduling_option | Temporarily hold a slot (2 min default, 10 min max) | Application-defined |
release_scheduling_option | Release a held slot | Yes |
confirm_scheduling_resolution | Create the booking after customer approval | Yes — requires approval |
reschedule_booking | Move to a new approved slot | Yes — requires approval |
cancel_booking | Cancel a booking | Yes — requires approval |
get_booking | Retrieve booking details | No |
list_professionals | List providers in the network | No |
get_slots | Get slots for a known provider | No |
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
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.