Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Multifamily real estate deal analysis — cap rate, DSCR, IRR, DFP Score, max offer price
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
DFP_API_KEYValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"dealflowpro": {
"command": "npx",
"args": [
"-y",
"dealflowpro-mcp"
],
"env": {
"DFP_API_KEY": "your-value"
}
}
}
}Run this in your terminal
claude mcp add dealflowpro --env DFP_API_KEY=your-value -- npx -y dealflowpro-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"dealflowpro": {
"command": "npx",
"args": [
"-y",
"dealflowpro-mcp"
],
"env": {
"DFP_API_KEY": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"dealflowpro": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"dealflowpro-mcp"
],
"env": {
"DFP_API_KEY": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account jbechtel-97, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: DFP_API_KEY
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.4.0) reached the registry 10 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, MemberVault MCP by usefulapi
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
List courses; add users to courses, remove course access or delete users in MemberVault.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Analyze multifamily real estate deals from Claude Code, Cursor, Claude Desktop, or any MCP-compatible client.
DealFlowPro is an AI-powered multifamily deal analysis platform. This MCP server wraps the DealFlowPro REST API, giving AI agents access to institutional-grade underwriting calculations.
Ask Claude naturally and it calls the right tool:
| Tool | Description |
|---|---|
analyze_deal | Full deal analysis: cap rate, DSCR, cash-on-cash, IRR, DFP Score (0-100), max offer price, yearly cashflows |
score_deal | Quick screening: DFP Score + key metrics |
reverse_calc | Max offer price from target returns (cap rate, CoC, DSCR, IRR) and an optional price-per-unit ceiling |
market_data | Flood zone, mapped wetlands, neighborhood income vs state median, rent burden, job growth for any US address |
All four carry MCP 2025-06-18 annotations (title, readOnlyHint, destructiveHint, idempotentHint, openWorldHint). Every tool is read-only.
This repo doubles as a Claude Code / Cowork plugin. The plugin connects to the remote server at https://dealflowpro.io/mcp rather than the npm package above, which means:
list_my_deals, get_deal_analysis, get_my_criteria, and portfolio_summary — your saved deals, buy-box criteria, and pipeline, scoped to your account.DFP_API_KEY to export; you sign in to your DealFlowPro account when the plugin connects.claude --plugin-dir /path/to/dealflowpro-mcp-server
Use the npm package below instead if you want a local stdio server, prefer API key auth, or are wiring DealFlowPro into a non-Claude MCP client.
DealFlowPro is built to slot into AI eval pipelines and production AI stacks. The MCP server (this package, plus the remote endpoint at https://dealflowpro.io/mcp) wraps the same engine as the REST API — schema-strict, idempotent, predictable.
Auth + scoping. Every tool call is authenticated, with a Bearer API key or, on the remote endpoint, an OAuth sign-in. Calls are scoped to the account that issued the key or signed in — no cross-tenant access path. Per-tool audit lines land in your account's logs/mcp_tool_calls.log capturing tool name + flattened arg keys (not values) — usage is auditable without exposing deal contents.
Rate limits per tier.
| Tier | Daily limit | Monthly | Cost |
|---|---|---|---|
| Free | 5 requests, lifetime | — | free, no card |
| Pay-as-you-go | balance-based | per credits | $1/request |
| Essentials | 50 req/day | ~1,500 | $79/mo |
| Premium | 200 req/day | ~6,000 | $149/mo |
| Enterprise | 1,000 req/day | ~30,000 | $399/mo |
Rate limit headers (X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset) returned on every response. 429 responses include Retry-After.
Error codes. Stable, documented at dealflowpro.io/api/docs/#errors — all errors are JSON {success: false, error: {code, message}} shape. Codes: invalid_input (400), invalid_json (400), unauthorized (401), tier_required (403), method_not_allowed (405), payload_too_large (413), rate_limit_exceeded (429), internal_error (500).
Tool schemas. Each MCP tool has a schema-strict input definition. Call tools/list against the remote endpoint to get the canonical schemas at runtime; the REST OpenAPI spec covers the same shapes for the four compute tools (analyze_deal, score_deal, reverse_calc, market_data). The four saved-pipeline tools on the remote server (list_my_deals, get_deal_analysis, get_my_criteria, portfolio_summary) are MCP-only and need an Essentials plan or higher.
Eval harness pattern. For benchmarking, the recommended pattern: maintain a fixture set of (deal payload → expected metrics) pairs, run each against score_deal (the lightest tool; each call still counts as one request, so budget for it under the tier table above), assert metrics within tolerance. The endpoint is deterministic — same inputs produce the same outputs.
Data handling. Request payloads are processed in memory and not persisted to disk. TLS 1.2+ in transit. Anthropic API calls (when DealFlowPro internally uses Claude for document extraction) flow through DealFlowPro's zero-data-retention Anthropic workspace. Full posture: dealflowpro.io/security#api-mcp-data-handling.
You have two install paths — pick the one that matches your client.
Use this for claude.ai web (Custom Connectors), Claude Code with HTTP transport, or Claude API mcp_servers. The endpoint is https://dealflowpro.io/mcp (Streamable HTTP, MCP 2025-06-18).
claude.ai web / Claude Desktop: DealFlowPro is listed in the Claude Connectors Directory, where you can add it directly, or you can add it yourself as a custom connector — Customize → Connectors → "Add custom connector" → name it DealFlowPro, paste https://dealflowpro.io/mcp → Add → Connect → sign in to DealFlowPro → click Allow. OAuth handles auth automatically (no API key to manage). Then in a chat, click "+" → Connectors → toggle DealFlowPro on.
Add DealFlowPro to Claude → — opens the dialog with the name and URL pre-filled. You still review and confirm before anything is added.
Team / Enterprise plans: members cannot add custom connectors themselves. An organization Owner adds it once under Organization settings → Connectors → Add → Custom (type: Web), and each member then connects their own DealFlowPro account from Customize → Connectors.
Claude Code (HTTP):
claude mcp add dealflowpro \
--transport http \ --url https://dealflowpro.io/mcp \ --header "Authorization: Bearer dfp_sk_your_key_here"
Claude API:
POST https://api.anthropic.com/v1/messages
anthropic-beta: mcp-client-2025-11-20
{ "mcp_servers": [{ "type": "url", "url": "https://dealflowpro.io/mcp", "name": "dealflowpro", "authorization_token": "dfp_sk_your_key_here" }], ... }
Get a Bearer key (free 5-request key, no card, or pay-as-you-go credits) at dealflowpro.io/api.
Full setup details + Connected Apps revocation: dealflowpro.io/api/docs#mcp.
Use this anywhere you want the MCP server running locally instead of remote — or for a client that has no remote-URL path of its own. Claude Desktop supports both: remote via Settings → Connectors, or the local config below.
1. Get an API key. Visit dealflowpro.io/api to claim a free 5-request key (no card) or buy pay-as-you-go credits. Delivered by email.
2. Add to your client.
Claude Desktop — claude_desktop_config.json:
{
"mcpServers": { "dealflowpro": { "command": "npx", "args": ["-y", "dealflowpro-mcp"], "env": { "DFP_API_KEY": "dfp_sk_your_key_here" } } } }
Claude Code:
claude mcp add dealflowpro -e DFP_API_KEY=dfp_sk_your_key_here -- npx -y dealflowpro-mcp
Just ask Claude about a deal. It automatically picks the right tool.
## Deal Analysis Results
DFP Score: 19/100 (Poor)
| Metric | Value |
|---|---|
| Cap Rate | 4.48% |
| DSCR | 0.86 |
| Cash-on-Cash | -1.95% |
| IRR | -12.17% |
| NOI | $89,524 |
$1,197,476 (binding constraint: cash-on-cash)
Full REST API docs at dealflowpro.io/api/docs
DealFlowPro automates multifamily underwriting for 2-200 unit properties. Upload a broker email or OM and get a full investment analysis in 10 minutes instead of 2 hours. Used by operators, syndicators, and PE firms to screen deals faster.
MIT