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
674,927 tools. Updated 2026-10-19 00:22
"A local vector-based search engine for personal documents" matching MCP tools:
- 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
- Combine metadata filters with vector similarity to retrieve relevant documents. Pre-filter by tags, numeric ranges, or full-text before KNN ranking.MIT
- Search indexed documents with BM25 to retrieve exact-term matches for error codes, IDs, and names, ensuring precise recall when vector search is insufficient.MIT
- Search for similar documents by vector similarity, with optional scalar filters like age > 25.Apache 2.0
- Replace documents matching a SQL predicate with new rows, one-for-one, using local embeddings when vectors are omitted.Apache 2.0Destructive
Matching MCP Servers
- AlicenseNot gradedqualityDmaintenanceIn-memory vector store with TF-IDF vectorization and cosine similarity search, paid per call via x402 micropayments.MIT
- FlicenseNot gradedqualityBmaintenanceEnables personal productivity management by exposing MCP tools to create, retrieve, list, update, complete, and delete tasks and calendar events, with validation and conflict detection.-
Matching MCP Connectors
Search and read UK guides on solar PV, heat pumps, batteries and MCS certification.
Congressional Documents — full-text search and retrieval over the official
- Find documents similar in meaning to a given record using vector search by entity and ID, returning the closest matches (10 by default).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
- Semantic (meaning-based) memory search across all six memory layers via Atlas Vector Search autoEmbed. Finds conceptually related memories even without keyword overlap. Complements keyword-based recall/query_layer.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
- Perform a KNN vector similarity search on vectors stored in Redis hash data structures, returning the nearest neighbors for a given query vector.MIT
- Converts plain text documents into dense vector embeddings and upserts them into a Zvec collection for storage.Apache 2.0
- Start a browser-based authorization, poll for user approval, and store the returned MCP personal token.MIT
- Search for similar vectors in Baidu Vector Database tables while filtering results by scalar attributes to find relevant data points efficiently.Apache 2.0
- Search across text, audio, and video documents using vector similarity to find relevant content and retrieve full document details.MIT
- Search across Telegram chats or within one chat. Filter by text, attachment kind, date, author, or tag; use local engine for morphology-aware results.MIT
- Search personal memory layers using vector similarity and keyword fusion to retrieve relevant episodic, semantic, or procedural information.AGPL 3.0
- Search for documents using content-based retrieval and metadata filters. Specify search class and property conditions to narrow results.Apache 2.0
- Retrieve relevant personal memories by searching across episodic, semantic, and procedural layers using vector similarity and keyword matching fused via reciprocal rank fusion.AGPL 3.0
- Search FHIR documents for relevant information using vector embeddings. Retrieve answers from indexed notes and documents with a query and document ID.MIT