Coactive AI
Coactive AI is the contextual-intelligence layer for modern media — a multimodal AI platform that indexes unstructured visual content (images and video) once and makes it queryable for search, contextual advertising, content operations, moderation, brand safety, and audience targeting. Data teams ingest assets from cloud storage, encode them with multimodal models, and then run natural-language and SQL queries, build custom visual Concepts and Dynamic Tags, generate video narrative metadata, detect celebrities, and assemble Context Studio ad packages. The REST API (OpenAPI 3.1.0, HTTP Bearer auth via a short-lived /login token, path-based versioning across api/v0, api/v1 and api/v3) exposes ingestion, datasets, search, concepts, queries, connections, user management, and system credentials on api.coactive.ai. Backed by a16z and Bessemer Venture Partners.
Real signal across most facets with visible, nameable gaps — the contract exists but is thin, or the portal is good while governance and commercial terms are absent.
API Evangelist profiles Coactive AI the way a machine reads it — 27 machine-readable artifacts across 22 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Coactive AI scores 53.8/100 (developing), with a separate agent-readiness read of 69/100 (agent native). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile Coactive AI
Each block below is one kind of artifact we hold for Coactive AI. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 22
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
Coactive AI agentic-search > agenticSearch API
The agentic-search > agenticSearch API from Coactive AI — 2 operation(s) for agentic-search > agenticsearch.
Coactive AI celebrity-detection API
The celebrity-detection API from Coactive AI — 7 operation(s) for celebrity-detection.
Coactive AI classification API
The classification API from Coactive AI — 1 operation(s) for classification.
Coactive AI concept API
The concept API from Coactive AI — 5 operation(s) for concept.
Coactive AI connections > connections API
The connections > connections API from Coactive AI — 5 operation(s) for connections > connections.
Coactive AI context-studio > adSegments API
The context-studio > adSegments API from Coactive AI — 1 operation(s) for context-studio > adsegments.
Coactive AI datasets > dataset API
The datasets > dataset API from Coactive AI — 2 operation(s) for datasets > dataset.
Coactive AI datasets > datasetConfig API
The datasets > datasetConfig API from Coactive AI — 1 operation(s) for datasets > datasetconfig.
Coactive AI datasets > encoder API
The datasets > encoder API from Coactive AI — 1 operation(s) for datasets > encoder.
Coactive AI dynamicTags API
The dynamicTags API from Coactive AI — 1 operation(s) for dynamictags.
Coactive AI ingestion API
The ingestion API from Coactive AI — 1 operation(s) for ingestion.
Coactive AI ingestion > ingest API
The ingestion > ingest API from Coactive AI — 6 operation(s) for ingestion > ingest.
Coactive AI ingestion > status API
The ingestion > status API from Coactive AI — 9 operation(s) for ingestion > status.
Coactive AI queries API
The queries API from Coactive AI — 9 operation(s) for queries.
Coactive AI search-metadata-filter API
The search-metadata-filter API from Coactive AI — 8 operation(s) for search-metadata-filter.
Coactive AI search > search API
The search > search API from Coactive AI — 10 operation(s) for search > search.
Coactive AI search-video > searchVideo API
The search-video > searchVideo API from Coactive AI — 1 operation(s) for search-video > searchvideo.
Coactive AI systemCredentials API
The systemCredentials API from Coactive AI — 2 operation(s) for systemcredentials.
Coactive AI userManagement API
The userManagement API from Coactive AI — 6 operation(s) for usermanagement.
Coactive AI video-narative-metadata > videoNarrativeMetadata API
The video-narative-metadata > videoNarrativeMetadata API from Coactive AI — 13 operation(s) for video-narative-metadata > videonarrativemetadata.
Coactive AI video-narative-metadata > videoSummarization API
The video-narative-metadata > videoSummarization API from Coactive AI — 1 operation(s) for video-narative-metadata > videosummarization.
Coactive AI video-scores > videoScores API
The video-scores > videoScores API from Coactive AI — 4 operation(s) for video-scores > videoscores.
Scroll within the panel for all 22 ·
MCP Servers 1
Model Context Protocol servers expose these APIs directly to AI agents. We profile them because agent-native access is the fastest-growing way this provider's capabilities actually get used.
Model Context Protocol servers that expose these APIs to AI agents.
coactive-ai-mcp.yml
MCP SERVERSecurity Posture 3
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Resources
Every other property we hold for Coactive AI — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 4
Portal, sign-up, and the first successful call
Documentation 3
Reference material describing how the API behaves
Agent Surfaces 5
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 5
Pagination, idempotency, versioning, errors, and events
Build 3
SDKs, sample code, and the tooling you integrate with
Access & Security 4
Authentication, authorization, and security posture
Operate 4
Status, limits, changes, and where to get help
Commercial 2
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API
Other 1
Properties that don't map to a standard resource type
← All providers · Data indexed from github.com/api-evangelist/coactive-ai · machine-readable index on apis.io