Data API
The Moonlit Data API gives applications direct access to the same Moonlit Data Layer that powers the MCP server. Search, retrieve, use the reference graph, and stream AI research from your own backend.
How it differs from MCP
The Data API and the MCP server are the two access modes within Moonlit Connect. Both read from the same Moonlit Data Layer.
Use the MCP server when you want Claude or any MCP-compatible client to research European law against Moonlit's enriched data layer. Use the Data API when you are integrating the data layer into your own backend, building a custom RAG pipeline, or operating an LLM-agnostic product surface.
Capabilities
Six search modes: keyword (with Boolean operators and sort options), semantic, hybrid, semantic-reranked, hybrid-reranked, and reference search. Five filter endpoints with hierarchical taxonomies for jurisdictions, document types, fields of law, sources, and semantic-enabled portals. Full document retrieval with structured metadata, citation counts, in-force status, and AI-generated summaries. Article-level traversal for composite documents.
Luna
Luna is a streaming legal research assistant exposed as a Data API endpoint pair. Initialize a session, send a question with optional jurisdiction scoping, receive the answer with inline citations over Server-Sent Events. Luna runs on the Moonlit Data Layer, so every citation resolves to a Moonlit document.
The two endpoints are initialize_chat and ask_question. Drop Luna into another product instead of building a research assistant from scratch.
Get started
- Quickstart : your first request in three steps.
- Reference : every endpoint, parameter, and response schema, generated from the live OpenAPI spec.
- Use cases : real integration patterns from teams in production.
Endpoint base
All Data API endpoints sit under https://api.moonlit.ai/v1.1. The reference page documents each endpoint with cURL, Python, and JavaScript examples generated from the live OpenAPI spec.