OpenSearch vs Upstash Vector API + MCP

OpenSearch

OpenSearch 3.9.0 runs vector, text and hybrid search under Apache-2.0, with an OpenAPI 3.1 description of its REST API and API keys limited by permission and index pattern. The owner runs the cluster, no status page or SLA comes with the software, and no tool in the MCP server sets a read-only or destructive annotation.

Upstash Vector API + MCP

$0.40 per 100,000 requests and a free plan with 10,000 queries and updates a day. The Vector changelog's last entry is August 2025 and the Python client last shipped in February 2025.

OpenSearch

1. Create the index with index.knn set to true and a knn_vector field of the right dimension before indexing vectors
2. Put the filter clause inside the knn query for filtering during the search. A filter outside it runs afterwards and can return fewer than k hits
3. Ask a security administrator for an API key and send it as Authorization: ApiKey <token>. The token is shown once and lasts 90 days at most
4. Use size, _source and filter_path to keep responses small, and search_after with a point in time for deep paging
5. Set OPENSEARCH_SETTINGS_ALLOW_WRITE=false on the MCP server unless writes are needed. GenericOpenSearchApiTool can call any endpoint

Upstash Vector API + MCP

1. Connect to mcp.upstash.com/mcp for Vector tools. npx @upstash/mcp-server has none
2. Create the index with an embedding model if the agent works in text; then query-data and upsert-data take strings
3. Give retrieval-only agents the index's read-only token, not the full one
4. Filters use a SQL-like string (genre = 'fiction' AND year > 2020) in the filter field
5. Ignore the FAQ line saying hybrid isn't supported. Pass queryMode HYBRID, DENSE or SPARSE on hybrid indexes