Marqo AI (Vector Search & Embeddings)

Marqo AI (Vector Search & Embeddings) MCP Connector for Claude

A+

Manage semantic search via Marqo — execute tensor queries, index JSON documents, and audit vector indices.

6 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Marqo instance to any AI agent and take full control of your semantic search infrastructure, vector embeddings, and real-time document indexing through natural conversation.

What you can do

  • Tensor Search Orchestration — Execute dense semantic similarity searches against your indices using natural language queries, with Marqo handling embedding extraction automatically
  • Dynamic Document Ingestion — Write new JSON records into your vector indices directly from your agent, allowing for instant searchability of fresh data mappings
  • Index Lifecycle Management — Create explicitly bounded new vector indices with custom model settings and dimension constraints to optimize your search architecture
  • Vector Audit & Stats — Retrieve detailed configuration metrics for your indices, including document counts, embedding model types, and underlying schema mappings
  • Precision Deletion — Physically eradicate vectorized representations by targeting specific scalar identifiers to maintain a clean and relevant search index
  • Resource Inventory — List all available vector indices on your Marqo instance to identify collection boundaries before executing search queries

How it works

  1. Subscribe to this server
  2. Enter your Marqo API URL and API Key
  3. Start optimizing your semantic search from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Search Architects — test semantic relevance and verify index configurations through natural conversation without manual API tools
  • Machine Learning Engineers — monitor vector index stats and verify document embedding results directly from your workspace
  • Software Developers — integrate AI-powered search results into applications and manage document lifecycles across multiple Marqo environments efficiently
semantic-searchvector-embeddingstensor-searchindexinginformation-retrieval

6 tools expose this connector's capabilities to your AI agent.

list_indexes

Crucial before writing queries hitting arbitrary collections. List all Marqo vector indexes

get_index_stats

Get configuration and stats for an index

tensor_search

Perform natural language tensor search on Marqo

add_documents

Write new documents into Marqo

delete_documents

Delete specific documents from Marqo by targeting their IDs

create_index

Create an explicitly bounded new vector index

See how to talk to your AI agent using Marqo AI (Vector Search & Embeddings).

Semantic search in index 'products' for 'lightweight running shoes for trails'

Executing tensor search… I've found 5 highly relevant products. Top match: 'Swift-Trail Runner' (Score: 0.89). Other results include specialized mountain gear and ultra-light hikers. Would you like to see the full JSON metadata for these matches?

List all vector indexes in my Marqo instance

I've identified 3 indexes: 'products' (Ecommerce catalog), 'support-docs' (Technical KB), and 'user-profiles' (Personalization data). Which one would you like to check the stats for?

Add this document to the 'support-docs' index: {"title": "API Auth", "content": "Use Marqo-API-Key header"}

Document added successfully to 'support-docs'. Marqo has vectorized the content using your configured embedding model. The document is now indexed and immediately available for semantic searches. Your new doc ID is 'marqo-12345'.

Yes. Marqo is an end-to-end engine. When you use the `tensor_search` tool, you provide natural language and Marqo handles the model inference and vector extraction under the hood, returning semantically relevant results immediately.

Related Connectors