994 servers · Data & APIs · Vector & Semantic Search
Vector & Semantic Search servers from Data & APIs, aggregated from every major registry, trust-ranked, and ready to install.
Provides semantic code search and indexing using vector embeddings and AST-based code splitting, enabling natural language queries across codebases with automatic file filtering and support for multiple embedding providers and vector databases.
Integrates with Chroma vector database to enable collection management, document operations, and vector search capabilities for knowledge bases and context-aware conversations.
Enables semantic search and retrieval of specialized coding skills from GitHub repositories and local directories, using vector similarity to match tasks with relevant bioinformatics, cheminformatics, and data analysis implementations.
Develop with Pinecone, the vector database built for knowledgeable AI.
Integrates with SVGMaker's API to generate SVGs from text descriptions, edit existing images, and convert bitmap images to vector format with customizable quality settings and real-time progress tracking.
Integrates with Recraft's image generation API to create and edit raster and vector images, apply custom styles, manipulate backgrounds, upscale images, and perform vectorization with fine-grained control over artistic properties.
Bridges Obsidian vaults through the Local REST API, enabling intelligent note management, knowledge discovery, and conversational access to personal knowledge bases with semantic search, daily note handling, and task-oriented operations designed for knowledge workers.
Provides persistent memory capabilities for coding assistants by automatically capturing tool usage, decisions, and patterns across sessions in a local SQLite database with hybrid search combining keyword and semantic similarity.
Stores entities and relationships in a Neo4j graph database with semantic search and temporal filtering, enabling persistent contextual memory for conversational systems through 10 specialized tools for creating memories, building connections, and querying knowledge graphs with configurable depth traversal.
Provides deep code analysis capabilities for software repositories, enabling pattern detection, architecture understanding, and knowledge management through a FastAPI server with Qdrant vector database integration.
Academic research server integrating Google Scholar, OpenAlex, Crossref, and Semantic Scholar for federated paper search, PDF ingestion, citation management, and manuscript validation.
Semantic search across Claude Code conversations using hybrid vector and keyword search, fully local with no API keys required.
Unified academic literature retrieval across Scopus, ArXiv, and Semantic Scholar databases.
Database integration with security and compliance. Supports: PostgreSQL, MySQL, ClickHouse, Snowflake, MSSQL, BigQuery, Oracle Database, SQLite, ElasticSearch and DuckDB.
Automatically discovers, configures, and manages other MCP servers through intelligent search and vector similarity matching, eliminating manual setup and API key management while providing automated configuration file modification and setup instructions.
Integrates web crawling with RAG functionality to enable website content retrieval, storage in vector databases, and semantic searching over crawled data for enhanced knowledge access
Enables semantic search over Zotero research libraries by extracting and chunking PDF text, embedding with Gemini API, and storing in ChromaDB to find relevant papers, search specific passages with context, and retrieve bibliographic metadata with precise page-level attribution.
Integrates with Milvus vector database to enable vector search, full-text search, and hybrid queries for semantic search and knowledge retrieval workflows.
Provides semantic search across a curated catalog of free public APIs using embedding-based natural language queries to help developers discover APIs by use case, retrieve detailed metadata including authentication and CORS requirements, and match requirements to available capabilities.
Connects AI systems to Qdrant vector database for semantic search capabilities through multiple embedding services, enabling efficient document management and similarity searches without leaving the conversation interface.
AI agent-native data platform for ingesting, validating, transforming, querying, and searching data across PostgreSQL, MongoDB, and vector databases.
Integrates semantic search and retrieval of documentation using a vector database (Qdrant), enabling efficient access to large document collections.
Transforms workspace documents into a searchable vector database using LanceDB and FastEmbed with hybrid search, version-aware ranking, and cross-session memory persistence.
Generates complete Python data pipeline scripts by automatically retrieving Airbyte connector specifications from a vector store and producing production-ready PyAirbyte code with error handling, environment management, and setup instructions for rapid ETL pipeline development.
Provides semantic search capabilities using a local Qdrant vector database and OpenAI embeddings for building private knowledge bases and document search systems without sending data to external services.
Semantic knowledge graph that indexes codebases into a local SQLite graph database for dead code detection, impact analysis, hotspot identification, and complexity reporting.
Unified GPU inference API exposing 30 AI services including LLMs, image generation, audio, video, and embeddings with x402 payment support.
Enables serial port communication with embedded devices and hardware through configurable connection parameters, multiple data encodings, and session management for IoT development, firmware debugging, and hardware automation.
Integrates with any OpenAPI-compliant service using dynamic tool generation and vector-based semantic search for efficient API operation discovery and interaction.
Integrates with Apple Notes to enable listing, searching, creating, and indexing notes using semantic and full-text search capabilities, leveraging LanceDB for efficient data storage and on-device embeddings for natural language interactions.
Provides persistent memory for Cursor through vector-based semantic search and structured data storage, enabling long-term context awareness across sessions by storing conversations, code snippets, and files with automatic embeddings for similarity-based retrieval.
Self-hosted AI memory layer with hybrid semantic and keyword search, backed by Postgres and pgvector.
Integrates with Google's Vertex AI and Discovery Engine APIs to enable advanced search and retrieval operations on large datasets, supporting semantic search and natural language understanding.
Provides semantic search and natural language querying of Ethereum blockchain data including addresses, transactions, blocks, tokens, and smart contracts with vector similarity matching and LLM-guided filtering across 150+ searchable parameters.
Academic paper search and citation management with 9 tools spanning OpenAlex, Semantic Scholar, Crossref, arXiv, and Unpaywall.
Provides persistent conversation history, semantic search, and API-level caching for Gemini models to optimize token usage and reduce costs.
Integrates with Wazuh security platform to provide real-time security alerts and event data from Elasticsearch indices for security operations and threat analysis workflows.
Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools.
Integrates with the Ontology Lookup Service API to search biomedical ontology terms, retrieve detailed ontology information, explore term hierarchies, and discover semantically similar terms across standardized ontologies like Gene Ontology and Human Phenotype Ontology.
Read-only SQL, MongoDB, Redis and Elasticsearch access, switchable mid-conversation.
Semantic codebase search + persistent working memory for AI code editors. Local, no API key.
Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.
Market regime, 7-dimension risk vectors and payment hazard grades. Abstains when data is thin.
Search and download academic papers from arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, Semantic Scholar, and IACR. Fetch PDFs and extract full text to accelerate literature reviews. Get consistent metadata for easier filtering, citation, and analysis.
MCP server for Forge, Voxell's embedding API. Voxell's Ingot-8B-R3 ranks #1 for English on MTEB.
Discover, resolve, and query official Brazilian economic data with semantic search and provenance.
RabbitMQ + Elasticsearch + Postgres Stack Generator (Mongo)
Semantic search over Handsontable and HyperFormula docs, API reference, release notes, and issues.
Bible corpus MCP server: scripture, Greek/Hebrew interlinear data, cross-refs, semantic search.
Governance validation for Semantic Data Charter instances; returns OASIS XACML decisions.
FAQ
994 Vector & Semantic Search MCP servers are indexed on Lulu MCPs, ranked by trust score and aggregated from the official MCP Registry, Glama, PulseMCP and Smithery. Every listing links back to its source registry and installs in one click for Claude Code, Cursor and VS Code.
Vector & Semantic Search is a sub-filter within Lulu MCPs' Data & APIs category, matched against a validated term set specific to vector & semantic search. Servers can appear under more than one sub-filter when their functionality spans multiple areas.
