MCP For Claude Marketplace
Typesense Vector Search

Typesense Vector Search MCP Connector for Claude

A+

Automate vector similarity searches via Typesense — index documents, manage collections, and execute semantic queries directly from your AI agent.

6 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your Typesense Vector Search environment to any AI agent and take full autonomous control over vector collections, indexing processes, and semantic querying through daily conversation.

What you can do

  • Vector Semantic Search — Issue combined text-filtering alongside vector similarity (vec) queries natively through chat
  • Collection Provisioning — Instantly create new semantic schema datasets holding complex vector embedding structures organically
  • Document Indexing — Let your AI insert or update JSON payloads into your database, bypassing manual code-level REST integrations
  • Schema & Records Insights — Retrieve absolute schema geometries mapping collections to ensure developers map fields correctly

How it works

  1. Subscribe to this connected MCP server
  2. Provide your active Typesense Host URL alongside an Admin API Key
  3. Start fetching vector similarities natively across Claude, Cursor, or your specific MCP workspace

No digging into CURL terminal payloads or writing Python scripts for basic document mutations. Your agent performs all indexation logic flawlessly.

Who is this for?

  • AI Application Builders — prompt the agent to create semantic collections supporting float[] logic seamlessly
  • Data Engineers — let the AI ingest missing RAG reference documents manually into a running collection
  • Backend Devs — perform sanity checks and text-filtered semantic searches inspecting exact relevance scores
vector-searchsemantic-searchragembedding-managementdocument-indexing

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

search_vectors

Provide the collection name, a text query, and a vector_query string (e.g., "vec:(0.1, 0.2, ...)"). Performs a vector similarity search combined with optional text filtering

create_collection

Provide the schema details as a JSON object. Creates a new search collection with a specific schema

delete_document

This action is irreversible. Permanently removes a document from a collection by its ID

get_collection_details

Retrieves schema and metadata for a specific collection

index_document

Provide the collection name and the document data as a JSON object. Adds or updates a document in a search collection

list_vector_collections

Lists all collections in the Typesense instance

See how to talk to your AI agent using Typesense Vector Search.

List all active collections on this vector cluster. Do I have any collections initialized yet?

I've listed 2 active collections: 'customer_kb_index' (configured with a 1536-dimensional embedding schema) and 'products_inventory'. Need me to execute a vector search on either limit?

I have an embedding snippet: [0.34, 0.42, 0.99...]. Delete the document carrying ID 'test-123' and re-index it using this JSON data on collection 'faqs'.

Document 'test-123' has been successfully wiped. I've seamlessly pushed the new JSON package into 'faqs', updating the embedding vectors as instructed.

Explain the schema definitions used inside the 'products_inventory' collection.

The collection 'products_inventory' uses 4 strict fields: `product_id` (string), `name` (string), `popularity` (int32), and critically `embeddings` formulated as a `float[]` of 768 dimensions representing product semantics.

Yes. Provide the agent with the collection name alongside the text payload and tell it the exact vector structure. It leverages internal filters querying natively and returns the nearest neighbors with exact accuracy scores.

Related Connectors

RA

Ragas MCP

7 tools Official

Equip your AI with Ragas to create datasets, run RAG evaluations, and track experiment metrics directly from your workflow.

A+ View details →
GG

GamerPower Gaming Giveaways MCP

11 tools Official

Find and track free gaming giveaways — get Steam keys, Epic Games Store offers, and in-game loot via AI.

A+ View details →
JU

Judge.me MCP

10 tools Official

Manage product reviews, questions, and ratings via Judge.me API.

A+ View details →
NI

Nimbleway MCP

10 tools Official

Web data collection and scraping via Nimbleway — extract content and search the web directly from your AI agent.

A+ View details →