Connect Claude, ChatGPT or your own agents straight into REAP. Underwrite any address, pull your pipeline and write deals back — without leaving the tool you already work in.
Enterprise add-on · limited preview seats
REAP MCP is a Model Context Protocol server. You paste one URL and key into your AI client, and REAP becomes a set of tools your assistant can call on its own — in the middle of a sentence, without you switching windows.
Your assistant can see the deals you already have, so it answers about your portfolio instead of guessing.
The same models behind the REAP Score, called directly. Flip or hold, on a deal you have never entered.
Analysis that stays in a chat window is lost work. Your assistant writes results into REAP where your team sees them.
A score on its own is a guess you can't check. Every call returns the working underneath it — where the rent goes, what drove the score, and what breaks the deal.
Six read tools are running in production today. The underwriting and write tools ship to preview accounts at launch.
| Tool | What it does | Status |
|---|---|---|
list_deals | Deals in your pipeline, filtered by status | Live |
get_deal | One deal by address: full underwriting, units, recent activity | Live |
search_deals | Search by city, status, price band or property type | Live |
deal_units | Unit-level rent roll, in-place versus market | Live |
deal_documents | Documents attached to a deal | Live |
pipeline_summary | Counts and dollar totals by status | Live |
underwrite_deal | Run flip or hold underwriting on any address and price | At launch |
value_property | ARV, price per SF and valuation band | At launch |
rental_comps | Comparable rents with source and distance | At launch |
reap_score | The score plus the factors that produced it | At launch |
save_deal | Write a new deal into your REAP pipeline | At launch |
update_deal | Update assumptions, status or notes on an existing deal | At launch |
Preview accounts get the full set. Tool names and schemas may change before general availability — we version the endpoint so nothing breaks underneath you.
No SDK, no integration project, no engineer required for the standard clients.
We issue a key scoped to your organization. It sees your deals and nothing else.
Paste the URL into your AI client's connector settings, or into your agent's config file.
"Underwrite 4214 W Virginia at $1.95M." Your assistant picks the tools itself.
// Any MCP-compatible client { "mcpServers": { "reap": { "type": "url", "url": "https://mcp.getreap.ai/v1?key=YOUR_KEY" } } }
A key that reaches into your deal record deserves more than a shared password. Every one is scoped, logged and revocable on its own.
A key that reaches your deal record is not a password to hand around. Every key sits at exactly one scope, carries its own tool list, and dies on its own.
The contractor's key above was revoked at 4:12pm. Nobody else re-authenticated. Nothing else moved.
A key only ever returns your organization's deals. There is no cross-tenant read path.
Issue read-only keys to analysts and partners. Write access is granted per key, not by default.
Tool, arguments, timestamp and key, visible to your admins. You can see what your agents did.
Kill a key without rotating anyone else's. Contractor leaves, key dies, nothing else moves.
Your deals are not used to train models. Ours or anyone else's.
Per-key ceilings so a runaway agent cannot drain your credits overnight.
An agent with tools works the listing that lands at 11pm. This is one real week of calls, by hour.
MCP access is an Enterprise capability. If you are underwriting a handful of deals a month, Pro is the better fit — start there and move up when the volume justifies it.
Enterprise starts at $1,500/mo, annual contract.
We are onboarding preview accounts in small batches so every one gets a real setup call. Tell us what you would build and we will come back with a slot.
No spam. We use this to size the preview and nothing else.
We'll email you within two business days with a preview slot and your setup call link. Questions in the meantime: hello@getreap.ai
Give your assistant the engine instead. Preview seats are limited and onboarding is hands-on.
Request access