TehProf Booking MCP Server
MCP server that connects AI assistants to the TehProf Booking platform for checking real-time availability and managing reservations.
README
TehProf Booking MCP Server
Reservations & online scheduling via Model Context Protocol. Connect any MCP-compatible assistant (Claude, ChatGPT, Cursor, Cline) to a live booking system — check real-time availability and create reservations, no custom integration code.
TehProf Booking (booking.tehprof.kz) is a SaaS reservation and online-scheduling platform for hotels, resorts, nightly rentals, salons, clinics and real-estate agencies — a single resource calendar with money tracking, a public booking page, an embeddable widget and native Bitrix24 integration. This server exposes 8 AI tools over the platform's public REST API.
Zero installation: use the hosted endpoint at https://booking.tehprof.kz/mcp.
Published in the official MCP Registry as kz.tehprof.booking/reservations.
Quick Start
Claude Code:
claude mcp add --transport http tehprof-booking https://booking.tehprof.kz/mcp
Claude Desktop / other MCP clients (Streamable HTTP):
{
"mcpServers": {
"tehprof-booking": {
"type": "streamable-http",
"url": "https://booking.tehprof.kz/mcp"
}
}
}
With an API key (enables reservation management):
{
"mcpServers": {
"tehprof-booking": {
"type": "streamable-http",
"url": "https://booking.tehprof.kz/mcp",
"headers": { "Authorization": "Bearer bk_live_..." }
}
}
}
Tools
Anonymous (by a company's public slug — e.g. the slug from its public booking page booking.tehprof.kz/p/<slug>/):
| Tool | What it does |
|---|---|
get_branding |
Company profile: name, tagline, contacts, branding |
list_resources |
Bookable resources (rooms, cabins, specialists, properties) with pricing info |
list_groups |
Resource groups/categories |
check_availability |
Real-time availability for a resource and date range |
With an API key bk_live_... (issued in the Booking developer portal, scoped per tenant):
| Tool | What it does |
|---|---|
create_reservation |
Create a reservation (guest name, phone, dates) |
list_reservations |
List reservations with filters |
get_reservation |
Reservation status by id |
cancel_reservation |
Cancel a reservation |
Server Discovery
- Discovery card:
https://booking.tehprof.kz/.well-known/mcp.json - AI manifest:
https://booking.tehprof.kz/llms.txt· extended:/llms-full.txt - REST API docs (Redoc):
https://booking.tehprof.kz/api/public/v1/docs - OpenAPI 3.1 contract:
https://booking.tehprof.kz/api/public/v1/openapi.json
Architecture
This server is a thin, stateless Streamable HTTP wrapper over the Booking public REST API (/api/public/v1). It holds no data and no secrets:
- Bearer pass-through — your
bk_live_API key is never validated or stored by the MCP layer; it is forwarded to the REST API, where tenant isolation and scopes are enforced. - Anonymous tools work without any key.
- DNS-rebinding protection, loopback-bound upstream, no
Authorizationlogging.
MCP client ──Streamable HTTP──▶ booking-mcp ──HTTPS──▶ Booking public REST API
(this repo) (auth, scopes, tenant isolation)
Self-Hosting
The hosted endpoint is the recommended way to use this server. Running your own copy is mostly useful for development:
npm ci && npm run build
BOOKING_API_URL=https://booking.tehprof.kz MCP_HOST=0.0.0.0 npm start
Or with Docker:
docker build -t booking-mcp .
docker run -p 8107:8107 booking-mcp
Environment variables: MCP_PORT (default 8107), MCP_HOST (default 127.0.0.1), MCP_PUBLIC_URL, BOOKING_API_URL.
Security
- The MCP layer is read-only with respect to credentials: keys pass through to the REST API.
- Reservation writes require an API key with the
reservations:writescope; keys are tenant-scoped. - Anonymous surface exposes only what a company already publishes on its public booking page.
License
MIT © TehProf.kz
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.