kpi-dealflow-mcp
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., "@kpi-dealflow-mcp Add Jane Doe as a lead looking for a condo in Miami."
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.
kpi-dealflow-mcp
MCP (Model Context Protocol) server for KPI DealFlow — connect Claude, Cursor, or any MCP-compatible AI assistant directly to your real estate pipeline.
What it does
Gives your AI agent four tools:
Tool | Description |
| Add a new prospect to your pipeline |
| List and filter leads by stage or temperature |
| Pull full details on a specific lead |
| Move a lead through the funnel or update notes |
Related MCP server: Aspro Cloud MCP
Prerequisites
A KPI DealFlow account
An API key — generate one at Settings → API Access inside the app
Node.js 18 or newer
Setup
Claude Desktop (recommended)
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"kpi-dealflow": {
"command": "npx",
"args": ["kpi-dealflow-mcp"],
"env": {
"KPIDEALFLOW_API_KEY": "kpid_your_key_here"
}
}
}
}Config file locations:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Restart Claude Desktop after saving.
Other MCP clients
Any client that supports stdio MCP servers works the same way — point it at npx kpi-dealflow-mcp with your KPIDEALFLOW_API_KEY env var set.
Run directly (for testing)
KPIDEALFLOW_API_KEY=kpid_your_key npx kpi-dealflow-mcpUsage examples
Once connected, just talk to your agent:
"Add John Smith as a lead — he called in wanting to buy a 3-bed in Northampton, timeline is 90 days. Phone 413-555-1234."
"Who are my hot leads right now?"
"Move John Smith to Qualified Lead — we agreed to a buyer consultation Thursday."
"Show me all my Qualified Leads."
Environment variables
Variable | Required | Default | Description |
| Yes | — | Your API key from kpidealflow.com/settings |
| No |
| Override for self-hosted or staging |
License
MIT
Available Tools
4 toolsadd_leadA
Add a new lead to the KPI DealFlow pipeline. Use this when someone calls in, texts, emails, or is otherwise identified as a prospect.
Inputs: first_name (required), email, notes, phone, +6 more.
get_leadA
Get full details for a specific lead by ID.
Inputs: id (required).
list_leadsB
List leads from the KPI DealFlow pipeline. Filter by stage, status, or inbound/outbound.
Inputs: limit, inbound, lead_status, funnel_status.
update_leadB
Update a lead — move them through the pipeline, change their status, or add notes.
Inputs: id (required), notes, source, lead_status, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a distinct operation on leads: creation, listing, retrieval, and update. There is no overlap in purpose, making it easy for an agent to select the correct tool.
All tools follow a consistent verb_noun pattern with snake_case (e.g., add_lead, list_leads, get_lead, update_lead). The minor pluralization in list_leads does not detract from clarity.
Four tools is well-scoped for a lead pipeline server. Each tool serves a necessary function without redundancy, and the count falls comfortably within the 3-15 ideal range.
The tools cover the core lead lifecycle: add, list, get, and update. A delete tool is missing, but for many pipelines this may be intentional. Overall, the surface is adequately complete for common agent tasks.
Maintenance
Related MCP Connectors
Real estate CRM for Claude and ChatGPT: find leads and listings, report on pipeline, log follow-ups.
Real estate agency CRM: listings, clients, leads and viewings from your AI assistant (OAuth).
Manage SalesCloser AI sales agents, leads, campaigns and calls from your AI assistant.
AI lead-finder for agents: pull scored leads, draft replies in your voice, work the pipeline.
Related MCP Servers
- FlicenseBqualityDmaintenanceEnables AI assistants to autonomously interact with Kommo CRM, providing tools for managing pipelines, leads, contacts, and custom fields via the Kommo API v4.271-
- AlicenseBqualityDmaintenanceEnables AI assistants to manage CRM deals and tasks on Aspro Cloud, including CRUD operations on deals, tasks, users, pipelines, and workflows.16MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to look up real estate agents, search MLS listings, submit buyer/seller leads, and access proprietary seller-intent signals in SC and GA.MIT
- AlicenseCqualityBmaintenanceEnables AI assistants to work with the Follow Up Boss real estate CRM API through 130+ tools for operations like people, notes, deals, and smart lists, while keeping the user's API key local and delete operations opt-in.13362 npm1MIT