Simple File Vector Store

Filesystem

Achieve secure and efficient access to local file systems using the Model Context Protocol (MCP). Benefit from advanced features such as targeted editing, seamless search functionality powered by ripgrep, and smart context handling for extensive files and code repositories.

Milvus Vector Database

Enhance your search capabilities by linking with the Milvus vector database, facilitating vector search, full-text search, and versatile queries. Ideal for boosting semantic search and streamlining knowledge retrieval processes.

Memory PostgreSQL

Enhance your data recall with cutting-edge long-term memory functions leveraging PostgreSQL integrated with pgvector. This advanced setup allows seamless semantic search within stored data, empowering you to tag, score confidence levels, and filter information to uphold context continuity during interactions.

Pinecone Vector DB

Utilize Pinecone's vector databases to enhance semantic search capabilities and RAG functionality.

VikingDB

Unlock the power of data storage and retrieval with VikingDB vector database solution.

RAG Documentation Search

Enhances document search with semantic vectors for contextually relevant results from specified document repositories.

Milvus (Vector Database)

Enhance the connectivity between artificial intelligence platforms and the Milvus vector database to streamline semantic search, text retrieval, and hybrid data retrieval processes. This integration facilitates swift and accurate similarity matching and data extraction from vector datasets.

File Search Service

Experience seamless file search capabilities with an advanced Model Context Protocol (MCP). Effortlessly retrieve and browse through files in local directories, gaining access to comprehensive results that cover file attributes and content relevance.

File Finder

Enhance your networked environment with a cutting-edge Model Context Protocol (MCP) that leverages TypeScript and Node.js. Unlock seamless file search and retrieval functionalities through diverse execution modes, including standard and HTTP-based methods.

Qdrant Vector Database

Enhance your data retrieval with seamless semantic search features by leveraging the Model Context Protocol's integration with the Qdrant vector database. This cutting-edge protocol supports storage and access to data through various embedding sources, offering flexibility in deployment through Docker or local setups.

RAGDocs (Vector Documentation Search)

Unlock the ability to search and retrieve semantic documentation effortlessly through vector databases. Get URL extraction, source oversight, and index queuing, paired with diverse embedding providers such as Ollama and OpenAI.

LanceDB Vector Search

Unlock powerful vector search functions by leveraging LanceDB and Ollama's embedding model to conduct similarity searches within document collections seamlessly, eliminating the need for context switching.

LanceDB

Enhance your data capabilities with seamless integration with the LanceDB vector database. Enable streamlined storage, quick retrieval, and effective similarity search of vector embeddings paired with metadata. Ideal for boosting semantic search and recommendation systems' performance.

Code Embeddings

Enhance your code repository with a cutting-edge knowledge management solution powered by vector embeddings technology.

Memory Box

Enable seamless and contextual interactions by seamlessly integrating with Memory Box. Utilizing semantic memory storage, vector embeddings, and advanced search functions, this protocol ensures persistent and relevant user experiences.