Skip to content
Home

AdKit MCP

Matches ads semantically to AI app context using embeddings and vector search, with typed constraints and audit trails.

AdKit is a semantic ad engine that matches sponsor inserts to AI applications based on meaning rather than keywords. It solves the problem of brittle, keyword-based ad matching in LLM apps by using embeddings and vector search. The product targets teams building AI assistants, RAG search products, and content experiences, including developers and marketers in B2B companies. It is delivered as an MCP-compatible tool with a read-only runtime and a separate control plane for administration, ensuring security and auditability.

Key features

  • Semantic matching using embeddings and vector search
  • Typed targeting constraints (topics, locale, verticals)
  • Explainability with audit traces
  • Minimal MCP tool surface (match, explain, health, capabilities)
  • Dual-plane architecture for security
  • Batch ad ingestion and management
  • Collection management and schema migrations
Social posts
  • No social media activity within the last 30 days
GTM channels
  • API
  • Docs
ICP
  • Software developers
  • Product teams
  • Marketing teams