mcpField
B
BezBaseina

BezBaseina

Remote
bezbaseina.lvBusiness & Marketing0Updated 15w ago

About BezBaseina

BezBaseina is a remote MCP server for Latvia's property portal, serving people searching for rentals, sales, or nightly stays and owners managing listings. Public search is anonymous and read-only; owner changes require OAuth and separate confirmation for risky actions.

Key features

  1. 01Search rentals, sales, and nightly stays
  2. 02Retrieve listing details
  3. 03View market statistics
  4. 04Manage owner listings, photos, and prices
  5. 05Handle leads and AI assistance

Use cases

  1. 01Search Latvian properties for rent or sale
  2. 02Compare nightly-stay listings and market data
  3. 03Update a property listing or its photos
  4. 04Review leads and confirm a proposed price change

MCP support

Provides anonymous public search tools and a separate OAuth-protected owner toolset through Streamable HTTP. Risky owner changes use a two-step confirmation flow.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://bezbaseina.lv/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

3
ParameterTypeRequiredDescription
maxintegerNomax price EUR
minintegerNomin price EUR
citystringNocity slug, e.g. riga
dealenumNonightly | rent | sale | allnightly | rent | sale | all
kindenumNoapartment | house | land | commercial | any
limitintegerNomax rows (default 50, cap 200)
roomsstringNo1 | 2 | 3 | 4+

Details

From the project README

BezBaseina MCP Server

Remote MCP server for bezbaseina.lv — the Latvian property portal. Search rentals, sales and nightly stays across Latvia, get market statistics, and (as a property owner) manage listings, photos, prices and leads — from Claude, ChatGPT, Claude Code, Codex or any MCP client.

Published in the official MCP Registry as lv.bezbaseina/mcp.

Endpoints

EndpointAuthTools
https://bezbaseina.lv/mcpnonePublic read: list_public_listings, get_public_listing, market_summary
https://bezbaseina.lv/mcp/ownerOAuth 2.1 (PKCE + dynamic client registration)Full owner set (20 tools): create/edit/publish listings, photos, price changes, leads, AI assistance

Transport: Streamable HTTP (stateless JSON responses). Protocol versions 2024-11-05 … 2025-06-18.

Connect

claude.ai → Settings → Connectors → Add custom connector → URL https://bezbaseina.lv/mcp (public search) or https://bezbaseina.lv/mcp/owner (owner tools — opens BezBaseina login + consent; leave the OAuth fields empty). Works in the EU, on all plans.

ChatGPT → Settings → Connectors (enable Developer mode under Advanced if needed) → same URL.

Claude Code / any MCP client:

{ "mcpServers": { "bezbaseina": { "type": "http", "url": "https://bezbaseina.lv/mcp" } } }

Local stdio alternative (same owner toolset, token-based):

npx -y bezbaseina@latest mcp start

Safety model

  • Public tools are read-only and anonymous — no personal data collected.
  • Owner tools require explicit OAuth consent; access is revocable any time in the BezBaseina dashboard (Pārvalde → API).
  • Risky mutations (publish, pause, price change, delete) are two-phase: the tool returns a confirmation with a diff, and a separate confirm_action call applies it. Nothing changes silently.
  • Every tool carries readOnlyHint / destructiveHint annotations.

Discovery & docs

About

Built and operated by SIA Brain Club (Latvia) on the AI Martins platform. The server implementation is registry-driven — REST, OpenAPI, CLI and MCP all generate from one capability registry, so the surfaces never drift. This repository is the public home of the server (the implementation lives in the site's private monorepo); issues and questions welcome.

Comments

Markdown supported

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.