Search by meaning to retrieve paraphrases and synonyms, ranked by vector similarity; optionally pre-filter rows by a keyword condition first.
Apache 2.0
741,830 tools. Updated 2026-11-04 09:25
"A vector database for efficient similarity search and AI applications" matching MCP tools:
- Retrieve the k nearest nodes to a query embedding using HNSW vector similarity. Use for semantic search after creating a vector index on a specific label and property.Apache 2.0
- Initialize a new vector collection at a specified path, define its vector and scalar fields with optional indexes, and open it for use.Apache 2.0
- Retrieve the top-K most similar vertices to a query vector using vector similarity search. Provide vertex type, vector attribute, and query vector to get ranked results with distance scores.Apache 2.0
- Compute a deterministic similarity score between two embedding vectors using a selected metric like cosine. Validates equal vector lengths and returns the similarity score for comparison tasks.Apache 2.0
- Performs semantic vector search, then expands each result's graph neighborhood to reveal contextual relationships.Apache 2.0
Matching MCP Servers
- FlicenseNot gradedqualityBmaintenanceEnables stateless similarity search over pre-computed vector corpora using NMI and cosine fusion with entropy-calibrated weighting. Provides tools for ranking, scoring, outlier detection, and alpha calibration for AI agents.-
- AlicenseNot gradedqualityDmaintenanceIn-memory vector store with TF-IDF vectorization and cosine similarity search, paid per call via x402 micropayments.MIT
Matching MCP Connectors
Stateless NMI + cosine fusion with entropy-driven alpha calibration
Audits AI-crawler access, structured data and llms.txt on a site, and drafts the fixes.
- Combine metadata filters with vector similarity to retrieve relevant documents. Pre-filter by tags, numeric ranges, or full-text before KNN ranking.MIT
- Set up an HNSW vector index for fast similarity search on graph nodes. Requires label, property, dimensions, and metric to index existing and future vectors.Apache 2.0
- Run direct vector similarity search over records whose property is indexed with createEmbeddingIndex. Deprecated alias for vectorSearch; use vectorSearch for new integrations.Apache 2.0
- Search digital assets using vector or keyword queries. Use natural language filters to locate specific assets.ISC
- Search for similar documents by vector similarity, with optional scalar filters like age > 25.Apache 2.0
- Search Zvec vector stores by converting natural language queries into embeddings and retrieving similar items from a specified collection.Apache 2.0
- Search Code-Fundi repositories with semantic search, grep over docs, or grep over code. Returns matching files with similarity scores, paths, and optional documentation.MIT
- Retrieves ranked memory items from long-term AI memory using hybrid lexical and vector search. Supports point-in-time queries for factual lookup and technical recall.MIT
- Find relevant content across namespaces using natural language queries or vector similarity. Filter results by metadata or keywords for precise discovery.Apache 2.0
- Convert text into a numeric vector for semantic search, RAG, and similarity. Supports multiple languages.MIT
- Probe vector database endpoints for unauthenticated exposure and read-only fingerprinting across Weaviate, Qdrant, Chroma, Elasticsearch, Redis, and pgvector.MIT
- Generate vector representations for texts via Forge's hosted API to power semantic search, RAG, clustering, or similarity; use query/document input types.MIT
- Combine BM25 keyword and vector ANN semantic search in a single query. Adjust vector weight to balance between keyword-only and semantic-only retrieval, ideal for RAG when either alone falls short.MIT
- Search memories by natural-language query with optional importance and similarity filters. Returns ranked results with similarity scores.MIT
- Generate dense embedding vectors from text for similarity search using OpenAI's embedding API.Apache 2.0