Daft.ie MCP Server
Search and retrieve rental property details from Daft.ie via web scraping.
Dafty MCP Server

Disclaimer
This is an independent, open-source project and is not affiliated with, endorsed, or sponsored by Daft.ie. This tool is provided for educational and experimental purposes only. The data is scraped from a publicly available website, and its use is subject to the terms of service of that website. The author assumes no liability for the use or misuse of this software. Please use it responsibly and ethically.
This is an MCP (Model Context Protocol) server designed to interact with Daft.ie, primarily for searching rental properties via web scraping.
✨ Features
- 🔍 Search Rental Properties: Search for rental listings based on various criteria like location, price range, number of bedrooms, and property type. This tool uses web scraping.
- 📄 Get Rental Property Details: Attempts to retrieve detailed information about a specific rental property using its unique ID.
- Note: This tool relies on the official Daft.ie API (v3) which requires an API key. Without a valid key (set via the
DAFT_API_KEYenvironment variable), this tool will likely fail. Refer tosrc/daftApi.tsfor more details and a link to the Daft.ie API documentation.
- Note: This tool relies on the official Daft.ie API (v3) which requires an API key. Without a valid key (set via the
🛠️ Setup
-
Clone the repository:
git clone [YOUR_GITHUB_REPO_URL] cd dafty-mcp -
Install dependencies:
npm install -
Build the server:
npm run build -
Testing (Optional but Recommended): The project uses Vitest for unit testing. To run tests:
npm testTo run tests in watch mode:
npm run test:watch -
Configure MCP Settings: Add the following configuration to your MCP settings file (e.g.,
~/.config/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/mcp_settings.json):{ "mcpServers": { "dafty-mcp": { "command": "node", "args": ["~/dafty-mcp/build/index.js"], "env": {}, "disabled": false, "alwaysAllow": [] } } }
🚀 Usage
Once the MCP server is configured and running, you can use the following tools:
use_mcp_toolwithserver_name: "dafty-mcp"andtool_name: "search_rental_properties"use_mcp_toolwithserver_name: "dafty-mcp"andtool_name: "get_rental_property_details"
Example: Searching for rental properties in Dublin
<use_mcp_tool>
<server_name>dafty-mcp</server_name>
<tool_name>search_rental_properties</tool_name>
<arguments>
{
"location": "Dublin",
"min_price": 1000,
"max_price": 2000,
"num_beds": 2
}
</arguments>
</use_mcp_tool>
Example: Getting details for a specific property
<use_mcp_tool>
<server_name>dafty-mcp</server_name>
<tool_name>get_rental_property_details</tool_name>
<arguments>
{
"property_id": "1234567"
}
</arguments>
</use_mcp_tool>
Serveurs connexes
Bright Data
sponsorDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Intelligent Crawl4AI Agent
An AI-powered web scraping system for high-volume automation and advanced data extraction strategies.
Urlbox Full Page Screenshots
An MCP server for the Urlbox Screenshot API. It enables your client to take screenshots, generate PDFs, extract HTML/markdown, and more from websites.
Secure Fetch
Secure fetch to prevent access to local resources
DeepResearch MCP
A powerful research assistant for conducting iterative web searches, analysis, and report generation.
Patchright Lite MCP Server
A server that wraps the Patchright SDK to provide stealth browser automation for AI models.
Tap
AI forges browser automation as deterministic .tap.js programs. 140+ community skills, 3 runtimes. Programs run forever at $0.
HDW MCP Server
Access and manage LinkedIn data and user accounts using the HorizonDataWave API.
Crawl4AI
Web scraping skill for Claude AI. Crawl websites, extract structured data with CSS/LLM strategies, handle dynamic JavaScript content. Built on crawl4ai with complete SDK reference, example scripts, and tests.
MCP Undetected Chromedriver
Automate Chrome browser control while bypassing anti-bot detection using undetected-chromedriver.
Intercept
Give your AI the ability to read the web. Fetches URLs as clean markdown with 9 fallback strategies. Handles tweets, YouTube, arXiv, PDFs, and regular pages.