Welcome Aboard | Captain Docs

Captain is a deterministic File Search API for unstructured data.
Connect cloud storage, index files, and retrieve source chunks.

New to Captain? Start here to build your first collection.

Connect Claude Code, Cursor, or another MCP client in one step, no API code required.

Complete reference for all Captain API endpoints with examples.

Connect Captain to Claude, Cursor, or any MCP client in one command.

Keep a collection matched to a bucket automatically, with backfills and reconciliation.

The full list of documents, images, video, and audio formats Captain indexes.

File Search API

Deterministic Retrieval: Ask questions in plain English and get retrieved chunks with source metadata.
Cloud Storage Integration: Connect AWS S3 or GCS buckets and Captain processes and cleans files over a single API call.
Multi-Tenancy: Organize collections to scope different teams, folders, projects, etc.
Chunk-Level Workflow: Use stable chunk IDs, regions, custom metadata, and relations for source-grounded applications.
PII Masking: Redact sensitive text and faces before content is indexed. See PII Masking.

Complex Docs, Images, and Sheets

Captain can search across very large documents, text-heavy or visual images, and multi-faceted spreadsheets.

Automatic VLM, OCR, and computer vision pipelines support search over visual and text-heavy content.

Managed file indexing and deterministic retrieval for S3, GCS, or Azure Blob.