Filter documents by metadata before ranking by vector similarity to enable production RAG and semantic search pipelines.
MIT
260,856 tools. Last updated 2026-07-05 08:54
"Semantic search, RAG, and memory systems" matching MCP tools:
- Check the local memory engine's running status, stored-memory count, and semantic search availability. Use to confirm the engine is up before retrying failed operations.AGPL 3.0
- Search Redis documentation and knowledge base to find information on concepts, data structures, features, and use cases including caching, session management, and semantic search.MIT
- Convert text into numeric embedding vectors for RAG, semantic search, clustering, and similarity scoring. Supports multiple models and optional extra inputs.MIT
- Generate vector embeddings from text for semantic search, RAG, clustering, or similarity tasks. Choose between query or document input type and adjust model quality and dimensionality.MIT
- Extract recurring reflexion themes into semantic memory and prune outdated working memory to maintain relevant context.AGPL 3.0
Matching MCP Servers
- Alicense-qualityCmaintenancePersistent memory with semantic search for Claude and MCP-compatible clients, storing context that survives conversations and can be retrieved intelligently.Last updated1MIT
- Alicense-qualityBmaintenanceEnables AI coding agents to perform semantic code search locally, finding code by meaning rather than exact keywords.Last updated1MIT
Matching MCP Connectors
Medical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.
AI memory with 56 tools. Knowledge Graph, semantic search, OAuth 2.1 + Magic Link. Free tier.
- Parse code files into semantic chunks such as functions, classes, and methods to improve retrieval in RAG systems.MIT
- Search personal memory layers using vector similarity and keyword fusion to retrieve relevant episodic, semantic, or procedural information.AGPL 3.0
- Create a new vector store to organize documents for semantic search and RAG. Attach files, set expiration, and configure chunking strategy.MIT
- Generate embedding vectors for semantic search, RAG retrieval, and similarity scoring using IBM Granite models. Supports up to 64 texts per call with no IBM Cloud account required.Apache 2.0
- Search stored memories using natural language queries, balancing semantic relevance with memory freshness and importance. Returns both private and team memories when configured.MIT
- Combine BM25 keyword search with vector ANN in one pass. Adjust vector weight for balanced or pure BM25-only retrieval. Ideal for RAG when neither semantic nor keyword search alone suffices.
- Retrieve relevant UTCP documentation results using semantic search with enhanced relevance scoring and query expansion. Provides detailed match reasons for sophisticated search needs.MIT
- Search Beaker systems by hardware attributes: CPU, architecture, memory, pool, and more. All filters combine with AND logic.MIT
- Perform semantic search over agent memories, filtered by memory type and tags for precise retrieval.
- Parse code files into semantic chunks such as functions, classes, and methods to enhance RAG retrieval.MIT
- Generate text embeddings for retrieval-augmented generation, semantic search, and clustering. Each request costs $0.005 USDC.MIT
- Save facts, decisions, preferences, or lessons to long-term memory. Automatically create embeddings for future semantic search.MIT
- Parse code files into semantic chunks like functions, classes, and methods to improve RAG retrieval.MIT
- Search semantic memory for a project using natural language queries. Filter results by metadata for targeted retrieval.MIT