Vector Database MCP Servers

Compare MCP servers for vector databases, embeddings, semantic search, collection management, and RAG retrieval workflows.

Compare serversSearch Vector database

Matching MCP servers

Pulled from the existing MCP Servers directory with no separate topic database.

View all search results
Qdrant MCP
official
Semantic search using the Qdrant vector database.
View server
Qdrant MCP Server
Semantic code search using the Qdrant vector database and OpenAI embeddings.
View server
Qdrant RAG MCP Server
A semantic search server for codebases using Qdrant, featuring intelligent GitHub issue and project management.
View server
Workspace-Qdrant-MCP
Code knowledge and metadata with live update, knowledge library, semantic and vector searches
View server
Weaviate MCP Client
An MCP client for connecting to and interacting with a Weaviate vector database.
View server
ChromaDB MCP
An MCP server for vector storage and retrieval using ChromaDB.
View server
Chroma MCP Server
An MCP server for the Chroma embedding database, providing persistent, searchable working memory for AI-assisted development with features like automated context recall and codebase indexing.
View server
Embedding MCP Server
An MCP server powered by txtai for semantic search, knowledge graphs, and AI-driven text processing.
View server
gemini-embedding-2-mcp
A powerful Model Context Protocol (MCP) server using gemini embedding 3 that transforms any local directory into an ultrafast, visually-aware spatial search engine for AI agents.
View server
better-code-review-graph
Knowledge graph for token-efficient code reviews with Tree-sitter parsing, dual-mode embedding (ONNX + LiteLLM), and blast-radius analysis via MCP tools.
View server
MemoryMesh
Zero-dependency persistent AI memory using SQLite. Dual-store, pluggable embeddings, 10 MCP tools.
View server
SEC Filings and Earnings Call
The MCP server provides end-to-end workflows for SEC filings and earnings call transcripts—including ticker resolution, document retrieval, OCR, embedding, on-disk resource discovery, and semantic search—exposed via MCP and powered by the same olmOCR and embedding backends as the vLLM backends.
View server

Where Vector Database MCP fits

Connect agents to semantic search collections for RAG, support knowledge, code search, or research workflows.

Inspect vector collections, metadata, namespaces, and retrieval results from an MCP client.

Pair vector search with document extraction and knowledge retrieval pages for source-grounded answers.

Setup checklist

  1. 1Choose a server that supports your vector database and embedding workflow.
  2. 2Scope credentials to the relevant collections, indexes, or namespaces.
  3. 3Add the server configuration and API keys to your MCP client.
  4. 4Test a known semantic query and confirm returned results include metadata and source context.

How to choose

  • Check support for namespaces, filters, metadata, top-k controls, and score visibility.
  • Prefer read-only retrieval access before exposing ingestion or deletion tools.
  • Use separate collections for production knowledge, experiments, and user-uploaded content.

Vector Database MCP FAQ

What is Vector Database MCP?

Vector Database MCP connects agents to semantic search and embedding-backed databases through MCP so they can retrieve relevant context.

Is Vector Database MCP only for RAG?

RAG is the most common use case, but vector search also helps with recommendations, similarity lookup, code search, and knowledge discovery.

Which vector databases fit this topic?

Pinecone, Qdrant, Weaviate, Chroma, pgvector, and managed vector search services can fit when the workflow is semantic retrieval.