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
338,921 tools. Last updated 2026-07-30 05:16
"How to work with a vector database" matching MCP tools:
- Retrieves all supported vector database providers, including required and optional config fields and setup notes. Use this to prepare the configuration needed for syncing data to a vector database.MIT
- Create a vector index on a vector field in Baidu Vector Database to enable efficient similarity searches for AI applications.Apache 2.0
- Discover supported vector database providers and their required and optional config fields, along with setup notes, to prepare for syncing data.MIT
- Save research content to a vector database for semantic search and future retrieval, organized by topic for easy access.MIT
- Add multiple context entries to a vector database in one batch operation for efficient bulk indexing and storage of semantic information.MIT
Matching MCP Servers
- -license-qualityCmaintenanceA minimal MCP server with get_weather and create_ticket tools, used for testing MCP servers across protocol, unit, eval, transport, and auth layers.Last updated
- Alicense-qualityBmaintenanceIntegrates RAG into AI agents via MCP Server, supporting multiple vector database technologies for collection management and search operations.Last updated12MIT
Matching MCP Connectors
チームの働き方を支援するグループウェア Work Handler の MCP サーバー。組織・メンバーの参照、出退勤の共有、タイムカード、承認フロー等を本人の権限の範囲で操作できる。
Access comprehensive company data including financial records, ownership structures, and contact information. Search for businesses using domains, registration numbers, or LinkedIn profiles to streamline due diligence and lead generation. Retrieve historical financial performance and complex corporate group structures to support informed business analysis.
- List all documents stored in the vector database with pagination. Set limit and offset to navigate through results.MIT
- Store information in a vector database for later retrieval. This tool adds context entries with unique IDs, content, and optional metadata to enable semantic search capabilities.MIT
- Starts the Qdrant vector database container for vector search functionality in Hephaestus development, avoiding manual Docker setup.MIT
- Save new documents or text chunks to a Qdrant vector database for later retrieval, adding information to a knowledge base with metadata support.Apache 2.0
- Re-embed all memories in the vector database to refresh and update stored information for accurate retrieval.MIT
- Retrieve vector database statistics including stored context count and dimensions to monitor data volume and structure.MIT
- Convert skill directories into Weaviate-ready format for hybrid vector and keyword search. Enables production RAG applications with BM25 and vector retrieval.MIT
- Delete a document from the Chroma vector database by its unique ID. Remove outdated or incorrect entries to maintain accurate data.MIT
- Index a local project directory into a vector database to enable semantic code search and analysis across your codebase.MIT
- Retrieve vector database configuration details to understand storage setup and manage embeddings for AI applications.MIT
- Retrieve a document from a vector database by providing its unique ID.MIT
- Create, list, delete collections and add documents to vector databases for RAG workflows.MIT
- Add a document with content and metadata to the Chroma vector database using a unique document ID.MIT
- Update content and metadata of an existing document in the Chroma vector database using the document ID.MIT