OpenSearch Vector MCP Server
Run k-NN vector searches on OpenSearch — create indexes, upsert embeddings, query similar documents, and manage your vector store from any AI agent.
Vinkius AI Gateway supports streamable HTTP and SSE.
Works with every AI agent you already use
…and any MCP-compatible client
OpenSearch MCP Server: see your AI Agent in action
Built-in capabilities (6)
create_index
knn: true` and mapping a rigid dynamic dense vector field optimized for cosine similarity. Create a new native OpenSearch KNN index ready for vector embeddings
delete_document
Delete an explicit vector document bounding from OpenSearch
get_index
Retrieve explicit OpenSearch index mapping and settings
index_document
This executes a fast transactional atomic insertion into the embedding space. Upsert a singular vector document directly into an OpenSearch KNN index
list_indexes
List all explicit indexes residing on the OpenSearch cluster
search
Provide the exact index name and a JSON-stringified dense float vector array to find conceptually similar embeddings natively. Execute a K-Nearest Neighbors (k-NN) vector search against OpenSearch
What this connector unlocks
Turn your OpenSearch cluster into an AI-native vector database. Create k-NN indexes, upsert embeddings, run similarity searches, and inspect index configurations — all through natural conversation with your AI agent.
What you can do
- Vector Search — Execute k-Nearest Neighbors queries against any k-NN index with custom top-K limits and dense float vectors
- Index Management — List all cluster indexes with health status and document counts, or inspect a specific index's vector dimension, engine config, and distance metric
- Create Index — Provision new k-NN indexes optimized for cosine similarity with configurable vector dimensions (384, 768, 1536, etc.)
- Document Operations — Upsert vector documents with metadata, or delete documents from the embedding space by ID
How it works
1. Subscribe to this server
2. Enter your OpenSearch Host, Username, and Password
3. Start managing your vector store from Claude, Cursor, or any MCP-compatible client
Who is this for?
- ML engineers — test similarity queries against production embeddings without writing curl commands
- RAG developers — index and retrieve context documents for retrieval-augmented generation pipelines
- Data teams — inspect index health, document counts, and vector configurations through conversation instead of Kibana dashboards
Frequently asked questions
Give your AI agents the power of OpenSearch
Access OpenSearch and 2,000+ MCP servers — ready for your agents to use, right now. No glue code. No custom integrations. Just plug Vinkius AI Gateway and let your agents work.
More in this category
Prismic
10 toolsQuery and manage your Prismic headless CMS content — search documents, list custom types, and retrieve specific content directly from any AI agent.
Typesense Cloud
6 toolsAutomate search cluster workflows via Typesense Cloud — monitor performance metrics, check cluster health, manage aliases, and execute multi-searches.
Orkes Conductor
6 toolsOrchestrate microservice workflows via Orkes Conductor — list definitions, track running executions, search workflow history, and inspect task states from any AI agent.
You might also like
Upstash Redis
7 toolsEquip your AI to directly query, manage, and manipulate key-value data structures inside your serverless Upstash Redis databases.
General Motors
14 toolsAI connected car: control GM vehicles, check diagnostics, and track location via agents.
Slab
12 toolsManage your team's knowledge base — query wiki articles, create new documentation, and explore topics directly using AI agents.