Connectors
Connect the multimodal data warehouse to your existing stack with pre-built integrations. Plug in your data sources, then let multi-stage retrieval pipelines do the rest.
35 open source connectors available
Prebid.js RTD Adapter
Privacy-first contextual targeting for header bidding
A Real-Time Data (RTD) module for Prebid.js that replaces cookie-based targeting with contextual signals delivered in under 100ms. Enables multimodal content understanding for ad targeting without user tracking.
- -Sub-100ms latency for header bidding
- -Multimodal content analysis (text, images, video)
- -IAB v3.0 taxonomy classification
- +3 more
@mixpeek/prebid(npm)IAB Content Taxonomy Mapper
Migrate content taxonomy from IAB 2.x to 3.0
A local processing tool that migrates content categorization from IAB 2.x standards to IAB 3.0 format. Converts existing taxonomy codes into OpenRTB and VAST-ready category IDs with optional semantic enrichment using embeddings and LLM re-ranking.
- -Deterministic and fuzzy string matching
- -Multi-category output per input record
- -Local-first processing (no external APIs required)
- +3 more
iab-mapper(pypi)LangChain Integration
Give your AI agents eyes, ears, and memory
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.
- -MixpeekToolkit — 6-tool agent toolkit for LangGraph/LangChain agents
- -MixpeekRetriever with as_tool() one-line conversion for agents
- -VectorStore supporting all file types: text, image, video, audio, PDF, Excel
- +3 more
langchain-mixpeek(pypi)@mixpeek/langchain(npm)Strapi Plugin
Open-source CMS connector for content intelligence
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.
- -Lifecycle hook integration for auto-enrichment
- -Content-type builder field mapping
- -Admin panel UI for configuration
- +2 more
@mixpeek/strapi(npm)FHIR R4 Connector
Enrich clinical resources with multimodal AI
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.
- -Dedicated extractors for 7 core FHIR resource types
- -FHIR-compatible enrichment via extensions and meta tags
- -Automatic narrative text fallback for unsupported resource types
- +3 more
@mixpeek/fhir(npm)React SearchKit
Composable React components for multimodal search
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.
- -Full search widget with Cmd+K modal or inline embed
- -Stages streaming, watch results flow through search → rerank → enrich in real time
- -AI-generated answers with citations
- +3 more
@mixpeek/react-searchkit(npm)MCP Server
Give AI agents perception over multimodal data via the Model Context Protocol
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.
- -Semantic search across video, images, audio, and documents via natural language
- -IAB v3.0 taxonomy classification for any media file
- -Brand safety and logo detection tools
- +5 more
mixpeek-mcp(pypi)Prebid Server RTD Module
Server-side contextual enrichment for Prebid Server
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.
- -Spec-aligned OpenRTB 2.6 field mappings
- -Local testing harness without PBS deployment
- -Privacy-first with no cookies or user tracking
- +3 more
@mixpeek/prebid-server(npm)OpenRTB Enrichment Connector
Contextual AI signals for programmatic bid requests
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 sub-200ms response times.
- -Privacy-first contextual signals without PII
- -Sub-200ms real-time processing for RTB
- -Multimodal AI analysis (text, images, video)
- +3 more
@mixpeek/openrtb(npm)Cloudflare Workers Connector
Edge-deployed content intelligence for advertising and analytics
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.
- -Edge-first processing at Cloudflare infrastructure
- -Cloudflare KV caching for instant profile retrieval
- -Multi-format output (GAM, OpenRTB, Analytics, JSON)
- +3 more
Google Ad Manager Connector
Privacy-safe GPT targeting signals from page content
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.
- -IAB Taxonomy v3.0 and v2.2 category signals
- -Sentiment analysis (positive/neutral/negative)
- -Four-tier brand suitability classification
- +3 more
@mixpeek/google-ad-manager(npm)n8n Workflow Connector
Multimodal AI processing for workflow automation
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.
- -Auto-tagging of URLs, files, and media
- -Semantic search across documents and video
- -Content moderation and safety signals
- +3 more
@mixpeek/n8n-nodes-mixpeek(npm)What are Mixpeek Connectors?
Connectors are pre-built integrations that allow you to seamlessly incorporate Mixpeek's multimodal capabilities into your existing infrastructure and workflows.
Drop-In Integration
Install via npm or pip and configure with a few lines of code. No complex setup required.
Production Ready
Battle-tested connectors optimized for latency, reliability, and scale in production environments.
Open Source
All connectors are open source. Inspect the code, contribute improvements, or fork for custom needs.