paddling-pl-mcp-server
MCP server for paddling.pl, a Polish kayaking-trip marketplace, enabling users to search trips, check availability, and access equipment resources through natural language.
README
paddling.pl — MCP Server
A Model Context Protocol (MCP) server for
paddling.pl — a Polish marketplace aggregating kayaking-trip offers from
local operators across Poland, letting users discover routes, compare offers,
check availability, and book & pay online. Built to be hosted as a Vercel
Function / Next.js API route using the
mcp-handler package, following
the official
Vercel docs.
About paddling.pl
Paddling.pl is a kayaking-trip marketplace founded in 2025 and headquartered in Gdańsk, Poland. It gathers verified local organizers across Poland's voivodeships — from family-friendly one-day routes to multi-day expeditions — and digitizes booking: users find routes matched to their needs, check availability, and reserve & pay online in minutes, while organizers gain a modern channel to reach new customers. Its mission is to digitize and simplify the Polish kayaking market.
Endpoint
https://paddling-pl-mcp-server.vercel.app/api/mcp
For local development, the endpoint is served at http://localhost:3000/api/mcp.
Available tools
| Tool | Description | Arguments |
|---|---|---|
search_trips |
Lists kayaking trips, optionally filtered; includes a direct link per trip | voivodeships (array of region codes), dateFrom/dateTo (YYYY-MM-DD), minPersons (int ≥ 1), page (int ≥ 0), size (int 1–100) |
get_trip_availability |
Returns the available dates for a trip | tripId (UUID) |
get_trip_resources |
Source of truth for real equipment availability on a given date | tripId (UUID), date (YYYY-MM-DD) |
search_trips voivodeships accept any of: DOLNOSLASKIE, KUJAWSKO_POMORSKIE,
LUBELSKIE, LUBUSKIE, LODZKIE, MALOPOLSKIE, MAZOWIECKIE, OPOLSKIE,
PODKARPACKIE, PODLASKIE, POMORSKIE, SLASKIE, SWIETOKRZYSKIE,
WARMINSKO_MAZURSKIE, WIELKOPOLSKIE, ZACHODNIOPOMORSKIE, ZAGRANICA.
Trip links from
search_tripsuse the formhttps://paddling.pl/trips/{rentalSlug}/{tripSlug}.
For developers
Stack
- Next.js 16 (App Router) — hosts the MCP endpoint as an API route
- mcp-handler 2.x — turns the MCP server into a Web-standard HTTP handler
- @modelcontextprotocol/server 2 — the MCP protocol implementation
- zod 4 — input schema validation for tool arguments
- TypeScript 7
Getting started
npm install
npm run dev # http://localhost:3000
Test the server with the MCP Inspector via npm run inspect (see the
Vercel docs).
Project structure
app/api/mcp/route.ts # ← the MCP server (createMcpHandler + tools)
app/page.tsx # landing page
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
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.