Build on Lev's Platform | Lev Platform Docs

Choose Your Track

Most teams do not need the same entry point. Start where your implementation risk is lowest:

How to choose

If you want deterministic integrations and internal system sync, start with the REST API. If you want Claude, Cursor, or another client to work directly with Lev data and tools, start with MCP. If you want to ship a specific workflow quickly, start with a recipe and then branch into the reference docs as needed.

REST API

Integrate Lev into your product or data stack

Use structured endpoints, predictable envelopes, and machine-readable docs when you need sync jobs, back office automation, or product integrations.

Go to API Overview ->

MCP / Agents

Connect Lev to AI-native clients

Use Lev from Claude, Cursor, or another MCP-compatible client when you want tool use, retrieval, and human-in-the-loop workflows.

Go to MCP Setup ->

Recipes

Ship a real workflow faster

Use implementation recipes when you already know the workflow you want to build, from sync pipelines to a broker-facing copilot.

Browse recipes ->

Start by Job to Be Done

Use these starting points if you already know the workflow you want to ship:

Sync Lev into a warehouse or internal system

Start with Quickstart, then move to Pagination, Filtering & Sorting, and Data Sync Patterns.

Build a custom deal or CRM interface

Start with Deals, Contacts, Companies, and Account & Team.

Let an AI agent search lenders and compare terms

Start with MCP Setup, Agent Workflows, Lender Search, and Term Sheets.

Prototype a broker copilot

Start with Build a Broker Copilot for architecture, tool selection, retrieval patterns, and implementation order.

Persona starting points

Platform engineers: Focus on API overview, auth, pagination, and sync patterns first.
Product teams: Focus on the core resource pages and start with the objects you need to expose in your UI.
AI teams: Focus on MCP setup, agent workflows, lender search, and recipes that define the orchestration layer.
Broker operations: Focus on broker copilot, placements, term sheets, and account/team workflows.

What Lev Provides

The hard part is not building a UI anymore. The hard part is trustworthy CRE data, workflows, and intelligence. Lev gives you a shared foundation for all three tracks.

7,000+

lenders in the network

50,000+

contacts across capital sources

$50B+

transactions processed

800+

document types recognized

What Lev handles for you

CRE data model

Deals, financials, properties, term sheets, placements, contacts, companies, and their relationships.

Lender intelligence

Directory data, program matching, and ranked lender search based on live platform activity.

Automation layer

Agent-friendly workflows, MCP-compatible access, and orchestration primitives for repetitive work.

Platform controls

Auth, permissions, usage tracking, rate limits, and multi-tenant isolation.

First Builds

These are the fastest useful things to ship if you are starting fresh:

A first successful API read: Validate auth and fetch a small page of deals in under five minutes.
A durable sync job: Use cursor pagination, checkpoint storage, and idempotent writes to your own systems.
An AI-native lender search flow: Let an agent gather deal context, trigger lender search, and summarize the best next actions.
A broker copilot prototype: Combine deal retrieval, lender search, placements, and term sheets in one guided workflow.

Start with the smallest useful build

Choose the next doc based on what you want working today.

The best first step is the one that validates your riskiest assumption fastest, whether that is auth, MCP connectivity, or a production workflow recipe.

Recommended next steps

Quickstart MCP Setup Build a Broker Copilot

Authentication Quickstart API Keys Pagination Filtering & Sorting

Build on Lev with the right path from day one