Integrations

A Real-Time Data (RTD) module for Prebid.js that replaces cookie-based targeting with contextual signals, served from a cache so the auction waits only up to the auctionDelay you set. Enables multimodal content understanding for ad targeting without user tracking.

A local processing tool that migrates content categorization from IAB 2.x to IAB Content Taxonomy 3.1 IDs. Every 3.0 ID is also a 3.1 ID. Converts existing taxonomy labels into OpenRTB and VAST-ready category IDs, with cattax 9 for 3.1, and optional semantic enrichment using embeddings and LLM re-ranking.

The langchain-mixpeek package gives LangChain agents the ability to see video, hear audio, search images, and act on unstructured content. Includes a 6-tool agent toolkit (search, ingest, process, classify, cluster, alert), VectorStore with support for all file types, and bridge methods to convert between retrievers, tools, and toolkits.

Add multimodal content intelligence to your Strapi CMS with this plugin. It hooks into Strapi's lifecycle events to automatically process content through Mixpeek, enriching entries with taxonomy labels, embeddings, and structured metadata as content is created and updated.

A zero-dependency connector that extracts text from FHIR R4 clinical resources and enriches them with Mixpeek's multimodal AI. Supports Patient, Observation, Condition, DocumentReference, DiagnosticReport, Encounter, and MedicationRequest resources with automatic fallback to narrative text for all other types. Returns enrichment as FHIR-compatible extensions and meta tags.

A React component library for building multimodal search experiences. Drop in the full SearchKit widget or compose individual pieces, stages streaming, AI answers, filters, and theming included. Connects to any published Mixpeek retriever.

A Model Context Protocol (MCP) server that exposes Mixpeek's multimodal search, classification, and metadata extraction as agent-callable tools. Any MCP-compatible AI agent (Claude, ChatGPT, Cursor, Windsurf, Cline) can discover and invoke these tools to search video, classify images, extract metadata from documents, and detect brands or faces -- all through natural language.

A Node.js reference implementation for server-side OpenRTB bid request enrichment with Mixpeek's contextual signals. Provides spec-aligned field mappings identical to the Go-based Prebid Server data provider, enabling privacy-first contextual targeting without cookies or user tracking.

Enriches programmatic ad bid requests with contextual AI signals without user tracking. Processes OpenRTB requests through multimodal AI to deliver standardized enrichments in OpenRTB 2.5/2.6/3.0 formats, with a timeout so the bid flow never waits on it.

A shared content intelligence layer deployed at Cloudflare's edge that provides cached content profiles for advertising, analytics, and personalization systems. Implements a 'one analysis → many consumers' model where content understanding happens once at the edge, then distributes to multiple downstream systems.

A client-side utility that transforms page content into Google Publisher Tag (GPT) compatible targeting signals without cookies, user IDs, or auction latency. Generates custom targeting keys for IAB categories, sentiment, brand safety, and content depth that work with existing line items.

Transform URLs, text, images, and video into structured signals inside n8n workflows. Enables classification, semantic search, clustering, and ML inference on unstructured data with the pattern: Input → Mixpeek → Structured signals → Any system.