MCP Setup

MCP (Model Context Protocol) is an open standard that lets AI assistants use external services — here Locari — like a toolbox. Once connected, your assistant can retrieve applicant lists, edit listings, schedule viewings, and request documents without you opening the Locari interface.

Common Tasks

• Create a complete listing with AI
• Connect Claude
• Connect ChatGPT
• Connect Cursor, Windsurf, GitHub Copilot, or Cline
• Connect Gemini CLI
• Disconnect a connection
• Review active connections

Create a complete listing with AI

Once your assistant is connected to Locari, you can build a complete listing right in the conversation — guided, step by step, in your own language. You don't need to prepare anything or know which fields exist.

At the start, just send your assistant everything you have: photos of the apartment, the energy certificate, a few key facts, the address, and the base rent. The assistant sorts it all out for you and only asks about what's genuinely still missing.

How the conversation goes

The assistant walks you through the whole flow and checks in with you at every station:

1. Create a draft — the assistant sets up a new listing as a draft for you.
2. Address + location research — you give the address, the assistant automatically researches the location and nearby points (transport, shopping, schools, green spaces).
3. Key facts & finances — rooms, area, floor, base rent, utilities, and deposit.
4. Read the energy certificate — you upload the energy certificate, the assistant reads the values automatically.
5. Sort the images — the assistant puts your photos in a sensible order, and you can adjust the order.
6. Write the description — tailored to the listing, in one of four tone styles (e.g. factual, modern, or short and to the point), portal-compliant and multilingual on request.
7. Tenant profile & applicant criteria — in a short interview the assistant works out which applicants are a fit for you.
8. Privacy — the required privacy details are set together with you.
9. Contact & display — who the contact person is and how the listing should appear.
10. Quality check — the assistant checks the listing for completeness and points out any gaps.
11. Preview link — at the end you get one link to preview and activate.

You just confirm — the assistant handles the rest. If something's missing, it asks a targeted question instead of burying you in forms.

Safety & trust

• The assistant never completes the checkout itself — activation always goes through your single preview link.
• It does not export to portals on its own.
• Applicant criteria never lead to an automatic rejection — every application is reviewed manually.
• The listing and criteria are set up GDPR- and anti-discrimination-compliant.

More than listings

Your assistant can do more for you over MCP — with gathering information (location research, reading the energy certificate, reading documents, searching your portfolio) and with writing (four tone styles, portal-compliant). The day-to-day steering — applicants, viewings, and so on — is best done on the go via WhatsApp; see Locari on WhatsApp for more.

How To

You start every step in your user settings → Locari MCP. There you'll find the setup guide with an expandable section per client.

Connect Claude

1. Open user settings → Locari MCP and expand the Claude section.
2. In Claude Desktop open: Settings → Connectors → Add custom connector.
3. Name: Locari, URL: paste the displayed MCP URL — your browser opens for sign-in.

Connect ChatGPT

1. Open user settings → Locari MCP and expand the ChatGPT section.
2. In ChatGPT open: Settings → Connections → Add new MCP server.
3. Paste the MCP URL — your browser opens for sign-in.

Connect developer tools

For Cursor, Windsurf, GitHub Copilot, and Cline you use a JSON configuration.

1. Open user settings → Locari MCP.
2. Expand the desired client and copy the displayed JSON block.
3. Paste the configuration into the respective settings file:
   • Cursor: Settings → MCP → Add Server → Remote
   • Windsurf: Cascade → Model Context Protocol → Configure
   • GitHub Copilot: create .vscode/mcp.json in your workspace
   • Cline: Sidebar → MCP Servers → Advanced Settings

Sample configuration (Cursor / Windsurf / Cline):

{
  "mcpServers": {
    "locari": {
      "type": "url",
      "url": "https://locari.ai/api/mcp"
    }
  }
}

Connect Gemini CLI

1. Open user settings → Locari MCP and expand Gemini CLI.
2. Copy the configuration and paste it into ~/.gemini/settings.json.
3. Gemini CLI uses httpUrl instead of url.

Disconnect a connection

1. Open user settings → Locari MCP.
2. Locate the connection in the AI Integrations card.
3. Click the disconnect icon — access is revoked immediately.

Views and Fields

Connection table (AI Integrations)

• Client — name of the assistant that authorized the connection
• Last used — relative timestamp (e.g. "2 hours ago")
• Disconnect icon — revokes OAuth access immediately

What the assistant can see and do

The following action areas are available over MCP:

• Search and overview — query and filter listings, applicants, and properties
• Applicant management — retrieve evaluations, request documents, answer clarifications
• Communication — send messages to applicants and team members
• Viewings — create and reschedule appointments, send invitations
• Documents — manage folders, extract content
• Listings — create and edit rental cases, trigger portal export
• Notes and tasks — create internal notes and reminders

Audit and History

Every action an AI assistant executes over MCP is recorded in the history of the affected object (applicant, listing, document) with the actor "Locari AI" and a timestamp — identical to actions taken from the web interface.

Retention: History follows the same GDPR retention periods as all other activity. Disconnecting an MCP connection does not delete historical entries.

Related Pages

• Integrations — Overview
• Locari AI — Overview
• Settings — Overview
• Applicant Details
• Create listings