Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@vaultre-mcp List all new VaultRE enquiries from realestate.com.au and show the property."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Yes, ChatGPT, Claude and other AI agents can work in your VaultRE account. Cotlet.dev connects your own signed-in VaultRE account to any AI agent, so you can ask in plain words and the AI manages enquiries, contacts, properties and viewings for you.
List all new VaultRE enquiries from realestate.com.au and show the property and possible duplicate contact.
Process Priya Nair's enquiry for 14 Wattle Street and add a buyer requirement for the property.
Find contacts in the sales department whose email contains example.com and add a note to Priya's record.
Show this week's open homes and schedule a viewing for Alex Morgan on Saturday at 11 am.
Give me a weekly report of appraisals, listings and upcoming viewings for the sales team.
Related MCP server: Desktop Commander MCP (Transductive Edge Edition)
Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"Settings → Apps → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.
Copy .cursor/mcp.json from this repo into your project:
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1",
"headers": {
"Authorization": "Bearer ${COTLET_API_KEY}"
}
}
}
}This repo is a real MCP server. It speaks MCP over stdio, lists its VaultRE 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.
{"mcpServers":{"vaultre":{"command":"uvx","args":["vaultre-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}Or with Docker:
docker build -t vaultre-mcp .
docker run -i --rm -e COTLET_API_KEY vaultre-mcpTools: vaultre_guide, vaultre_status, vaultre_open, vaultre_read, vaultre_click, vaultre_type, vaultre_close. Without COTLET_API_KEY a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".
Python 3.10+, nothing else to install. From PyPI:
pip install vaultre-mcp # or run it once: uvx vaultre-mcp connect
vaultre-mcp connectOr straight from this repo:
export COTLET_API_KEY="your-key"
python3 vaultre_agent.py connect # ready config for Claude Code, Cursor, ChatGPT
python3 vaultre_agent.py status # is VaultRE ready in your Cotlet.dev account
python3 vaultre_agent.py guide # VaultRE screens and sign-in link
python3 vaultre_agent.py read # open VaultRE, read the page, close the browser
python3 vaultre_agent.py tools # list Cotlet.dev tools
python3 vaultre_agent.py serve # start the stdio MCP server (same as no argument)Does VaultRE have an API?
VaultRE, now sold as MRI Vault, has an API for approved developers, but no official MCP server (checked 27 Oct 2026). Cotlet.dev works in your own signed-in VaultRE account, so your AI agent can manage enquiries and property workflows with no API key and no code.
How do I connect VaultRE to ChatGPT?
Add Cotlet.dev as an app in ChatGPT with the connector URL https://cotlet.dev/mcp/v1, sign in to VaultRE once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words.
Is there a way to use Claude with VaultRE?
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 VaultRE account.
Is there a VaultRE MCP server?
VaultRE has no official MCP server. Cotlet.dev is a hosted MCP server that works in VaultRE with ChatGPT, Claude, Cursor, Codex, n8n, Make and scripts.
Start free: https://cotlet.dev/signup?app=vaultre&utm_source=github&utm_medium=readme&utm_campaign=vaultre
Click a numbered element on the current VaultRE page.
Inputs: element (required).
Close the VaultRE browser session when the work is done, so credits stop running.
Inputs: no named parameters.
How to work in VaultRE (manage enquiries, contacts, properties and viewings): its screens and the sign-in link. Call this first.
Inputs: task.
Open a VaultRE page in your signed-in Cloud Browser (default https://vaultre.com.au) to work with manage enquiries, contacts, properties and viewings.
Inputs: url.
Read the current VaultRE page: its text and numbered buttons, links and fields.
Inputs: element.
Check that your Cotlet.dev account and VaultRE are ready: account, credits and VaultRE connection.
Inputs: no named parameters.
Type text into a numbered field on the current VaultRE page.
Inputs: text (required), element (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 7 tools
Each tool has a clearly distinct role: reading, clicking, typing, guidance, status checking, opening, and closing. The boundary between vaultre_open and vaultre_guide is clear because one starts a session and the other provides instructions.
All tools follow a consistent vaultre_ + verb pattern: vaultre_read, vaultre_click, vaultre_type, vaultre_guide, vaultre_status, vaultre_open, vaultre_close. The convention is predictable and easy to scan.
Seven tools are well-scoped for a browser-automation server: a compact lifecycle of open, inspect, interact, check status, get guidance, and close. Each tool earns its place without redundant operations.
The surface covers the essential browser lifecycle and core interactions needed for VaultRE workflows. Minor gaps exist for specialized interactions like dropdown selection, file upload, scrolling, or waiting, but the read/click/type trio provides workarounds for most tasks.
VaultRE MCP server for ChatGPT, Claude and any AI agent: list enquiries, process enquiry, search contacts, add contact, add note, search properties, add appraisal and schedule viewing in your own VaultRE account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to VaultRE yourself; Cotlet does not store your password and you need no VaultRE API key. About the official VaultRE API: Yes, but only for approved integrators (checked 22 Oct 2026). VaultRE, now MRI Vault, publishes API docs, yet a developer needs an integrator key from MRI first, and the agency then creates an access token for that developer under Office Integrations > Third-Party Access. Setup and FAQ: https://cotlet.dev/integrations/vaultre-api-mcp-server
Connect ChatGPT, Claude, Cursor or VS Code to your Windows PC: files, terminal, browser, apps.
Connect AI assistants to your approved computer for files, commands, browser and desktop tasks.
Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.
