Starts the Qdrant vector database container for vector search functionality in Hephaestus development, avoiding manual Docker setup.
MIT
521,841 tools. Updated 2026-09-06 12:28
"Using Qdrant vector database for code indexing" matching MCP tools:
- Convert a skill directory into Qdrant vector database format, enabling high-performance search with native payload filtering.MIT
- Add an evidence bundle to a collection for semantic search and Q&A. Triggers async vector indexing; poll job status until complete.MIT
- Initialize the local knowledge base by creating the SQLite database, vector index, and required directories. Run once to enable all retrieval tools and fix missing database errors.MIT
- Locate code by natural language meaning, combining semantic vector search with graph analysis to surface relevant files, signatures, and dependencies for initial codebase discovery.MIT
- Search Qdrant collections by vector similarity, passing a query vector or combining multiple prefetch queries with RRF/DBSF fusion for hybrid retrieval.MIT
Matching MCP Servers
- AlicenseCqualityBmaintenanceA local-only codebase indexer that extracts syntax-aware chunks, creates embeddings locally, and enables semantic code search and symbol lookup via MCP.9MIT
- FlicenseNot gradedqualityDmaintenanceEnables semantic code search over a local codebase using Qdrant vector embeddings and OpenAI embeddings, allowing natural language queries from MCP-compatible clients like Claude Desktop.-
Matching MCP Connectors
Cloudflare Workers MCP server: code-explainer
- Travel CodeOAuth
Corporate travel: search and book flights, hotels, rail and transfers, manage orders.
- Analyze git diff between two refs to map changed files to wiki pages and code entities, or answer questions about the diff using RAG.MIT
- Splits clean text into overlapping chunks with unique IDs for vector embedding or search indexing.MIT
- Check the health of all memory components to confirm the backend is reachable before issuing recall queries. Provides per-component status for embedding, vector store, and graph database.Apache 2.0
- Check OpenLMlib database and vector index status to debug errors, verify initialization, or assess system readiness. Returns database size, finding count, and index status.MIT
- Indexes a codebase to build vector embeddings for semantic code search across 50+ languages. Required initial step before searching code.MIT
- Check the current index status, including database location, indexing state, total items, modules indexed, and progress if running.MIT
- List all Qdrant collections with their point counts to inspect and manage vector store contents.Apache 2.0
- Discover all vector columns in your PostgreSQL database, including table names and vector dimensions. Optionally filter by schema.MIT
- Remove a project's indexed codebase from the vector database, safely stopping file watchers, canceling pending indexing, and waiting for in-flight graph builds before deleting the index.AGPL 3.0
- Save research content to a vector database for semantic search and future retrieval, organized by topic for easy access.MIT
- Trigger manual indexing of all context artifacts, chunking and embedding them into the vector database for semantic search.AGPL 3.0
- Add multiple context entries to a vector database in one batch operation for efficient bulk indexing and storage of semantic information.MIT
- Ask questions about recent code changes and get answers synthesized from git diff and code context. Understand what changed, identify bugs, or assess impact without manual code review.MIT
- Retrieve integration documentation for databases, vector stores, and models. Specify the integration type and optional name to get targeted guides.MIT
- Set up a ChromaDB vector database with LangChain integration, storing text embeddings and optional metadata, with persistence support, returning a retriever.MIT