Perform advanced vector similarity search by combining a query vector with SQL filtering to find records matching both semantic and structured conditions.
MIT
744,135 tools. Updated 2026-11-04 22:08
"Understanding Vector Search" matching MCP tools:
- Activate vector search capabilities in Meilisearch to enable semantic similarity-based document retrieval using AI embeddings.MIT
- Activate vector search functionality in Meilisearch to enable semantic similarity-based document retrieval.-
- Apache 2.0
- Search a Qdrant collection by providing a raw vector to find similar items based on vector similarity, without needing a text query.Apache 2.0
- Configure embedders for vector search in Meilisearch indexes to enable semantic search capabilities.MIT
Matching MCP Servers
- AlicenseNot gradedqualityDmaintenanceIn-memory vector store with TF-IDF vectorization and cosine similarity search, paid per call via x402 micropayments.MIT
- FlicenseNot gradedqualityDmaintenanceCombines Neo4j graph database with vector search using OpenAI embeddings for intelligent semantic search across knowledge graphs.3-
Matching MCP Connectors
Hybrid sparse-dense neural search with cross-encoder re-ranking and semantic retrieval over streamable HTTP.
Search Vascue's public healthcare-ops, insurance-claims and booking docs. Public content only.
- Search Meilisearch indexes using vector embeddings to find semantically similar content, supporting hybrid text-vector searches and customizable filtering.MIT
- Configure embedders for vector search in Meilisearch indexes to enable semantic search capabilities.-
- Search for similar items in a Meilisearch index using vector embeddings to find content based on semantic similarity rather than exact text matches.-
- Search OpenMetadata entities using natural language queries with vector-based semantic matching.MIT
- Create a Databricks Vector Search endpoint by specifying its name and type (STANDARD or OPTIMIZED_STORAGE).MIT
- Get a list of Vector Search endpoints from your Databricks workspace.MIT
- Search cached Telegram messages with keyword full-text search, vector cosine search, or hybrid combination.-
- Query a Databricks Vector Search index using text or vector input to retrieve similar results with optional filters and scoring.MIT
- Search stored information using natural language queries to find semantically similar content in vector databases.-
- Search past screen capture OCR text to find when you saw specific content, error messages, or work references. Returns matching entries with timestamps and context.AGPL 3.0
- Combine results from multiple vector queries (e.g., dense + sparse) using weighted or RRF re-ranking to find relevant documents across different embedding spaces.Apache 2.0
- Search by meaning to retrieve paraphrases and synonyms, ranked by vector similarity; optionally pre-filter rows by a keyword condition first.Apache 2.0
- Enables keyword search by creating a full-text index on a node label and its string property. Existing and new nodes are indexed.Apache 2.0
- Search a channel's knowledge base using keywords. Deprecated: returns an error; use 'ask_channel' or 'search_channel_facts' instead.Apache 2.0
- Semantically search pre-indexed Materio documents. Get relevant text passages with similarity scores and source references to quickly find answers to your questions.MIT