How to connect Crexi to Claude Code, ChatGPT and any AI agent

Name: Crexi MCP Server and API by Cotlet
Author: cotlet

Yes, Claude, ChatGPT and other AI agents can work in your Crexi account. Crexi's Listing API is only for MLSs and large brokerages. Cotlet.dev connects your own Crexi account to any AI agent, so the AI searches listings, saves deals and tracks them for you.

What you can ask

Find retail properties for sale in Austin under $2M with a cap rate above 6%.

Save the 10 newest industrial listings in Phoenix to my "Q4 deals" list.

Compare these three listings: price per sq ft, cap rate, days on market.

Which of my saved properties dropped in price this week?

Export the contacts of brokers for my saved listings.

Connect in 2 minutes

Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.

Claude Code

bash

claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"

ChatGPT

Settings → Apps → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.

Cursor

Copy .cursor/mcp.json from this repo into your project:

json

{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}

Run it locally (stdio)

This repo is a real MCP server. It speaks MCP over stdio, lists its Crexi tools without any key, and forwards every tool call to the hosted Cotlet.dev server. The hosted URL above stays the recommended way. Use this when your client only starts local servers.

json

{"mcpServers":{"crexi":{"command":"uvx","args":["crexi-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}

Or with Docker:

bash

docker build -t crexi-mcp .
docker run -i --rm -e COTLET_API_KEY crexi-mcp

Tools: crexi_guide, crexi_status, crexi_open, crexi_read, crexi_click, crexi_type, crexi_close. Without COTLET_API_KEY a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".

Command line

Python 3.10+, nothing else to install. From PyPI:

bash

pip install crexi-mcp        # or run it once: uvx crexi-mcp connect
crexi-mcp connect

Or straight from this repo:

bash

export COTLET_API_KEY="your-key"
python3 crexi_agent.py connect   # ready config for Claude Code, Cursor, ChatGPT
python3 crexi_agent.py status    # is Crexi ready in your Cotlet.dev account
python3 crexi_agent.py guide     # Crexi screens and sign-in link
python3 crexi_agent.py read      # open Crexi, read the page, close the browser
python3 crexi_agent.py tools     # list Cotlet.dev tools
python3 crexi_agent.py serve     # start the stdio MCP server (same as no argument)

Questions from Crexi users

Does Crexi have an API?

Crexi has a Listing API only for qualifying MLSs, brokerages and data providers. Cotlet.dev works in your own Crexi account, so your AI agent can search and track deals without it.

How do I connect Crexi to ChatGPT?

Add Cotlet.dev as an app in ChatGPT (Settings → Apps, connector URL https://cotlet.dev/mcp/v1), sign in to Crexi once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words. No code and no Crexi API key.

Is there a way to use Claude with Crexi?

Yes. In Claude Code run the one-line claude mcp add command above; in the Claude app add https://cotlet.dev/mcp/v1 as a custom connector. Claude then works in your own Crexi account.

Is there a Crexi MCP server?

Crexi has no official MCP server. Cotlet.dev is a hosted MCP server that works in Crexi for you, 24/7, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier.