# research

research gives AI agents access to UK property records, area crime data, school ratings and demographics, with comparable listings for property valuation.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 2
- Author: Propbar
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Propbar/mcp
- Updated: 2026-02-02
- HTML: https://affpapa.org/en/nevibecode/mcp/research

## What it does

Built by Propbar, research connects an AI coding assistant to tools for exploring property and neighbourhood data across the UK. Agents can look up areas by name or postcode, search for homes by address, and retrieve crime statistics, Ofsted school ratings and census demographics. Property lookups also return basic details or a fuller record with historical information.

The `get_comparables` tool supports property valuation workflows. It filters similar homes by coordinates and attributes such as property type and bedroom count. Returned fields can cover past sale prices, current asking prices, floor area, EPC ratings, listing status, price per square foot and lease-related charges. An agent can use those results to build an automated valuation model (AVM).

The service uses Streamable HTTP at `https://mcp.propbar.co.uk` and authenticates through OAuth 2.1 with Supabase. A Propbar Pro or Plus subscription and an account are required. Claude Code and Codex each have a dedicated command for registering the server; Cursor and GitHub Copilot use configuration entries instead.

## Requirements
- Remote server: `https://mcp.propbar.co.uk`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http research https://mcp.propbar.co.uk
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add research --url https://mcp.propbar.co.uk
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "research": {
            "url": "https://mcp.propbar.co.uk"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "research": {
            "type": "http",
            "url": "https://mcp.propbar.co.uk"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http research https://mcp.propbar.co.uk
```

## When to use it
- Find UK homes by address or postcode
- Compare recent sales for similar properties
- Estimate a home's value from comparable listings
- Check neighbourhood crime statistics
- Review nearby schools and local demographics

## Example prompts
- Find comparable two-bedroom flats near these coordinates and compare their sale prices from the last 12 months.
- Check crime figures, Ofsted school ratings and census demographics for this postcode.
- Retrieve the property's history and compare its floor area, EPC rating and tenure with similar homes.

## Similar
- [Zotero MCP](https://affpapa.org/en/nevibecode/mcp/zotero-mcp.md) — MCP server · ★ 5585
- [arxiv-mcp-server](https://affpapa.org/en/nevibecode/mcp/arxiv-mcp-server.md) — MCP server · ★ 3235
- [PaperBanana](https://affpapa.org/en/nevibecode/mcp/paperbanana.md) — MCP server · ★ 2418
- [MATLAB MCP Server](https://affpapa.org/en/nevibecode/mcp/matlab-mcp-server.md) — MCP server · ★ 1723
- [Hex Research](https://affpapa.org/en/nevibecode/mcp/hex-research.md) — MCP server · ★ 584
- [DocsAgent — Zotero, Obsidian & Apple Notes MCP Server](https://affpapa.org/en/nevibecode/mcp/docsagent-zotero-obsidian-apple-notes-mcp-server.md) — MCP server · ★ 578

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md