Best Vector search MCP servers
Vector search MCP servers let an agent store and retrieve information by meaning rather than exact keywords, backing retrieval-augmented workflows and giving the agent a durable semantic memory. Through these tools an agent can embed and upsert documents, run similarity queries, and pull back the most relevant chunks to ground its next answer — useful for code search, knowledge bases, and long-running context. The main choices are deployment and embedding strategy: some servers run a local or embedded store for quick experiments, others connect to a managed cloud index built for scale, and they differ in whether embeddings are computed inside the server or handed off to a provider. Look at how collections and metadata filtering are exposed, and scope credentials to the specific index the agent should touch.
7 servers
LanceDB
Adiom
A maintained MCP server for agentic RAG over a local LanceDB index: hybrid search across a document catalog and its chunks.
Qdrant
Qdrant
Qdrant's official MCP server: a semantic memory layer that stores and retrieves information from a Qdrant vector database.
Chroma
Chroma
Chroma's official MCP server: manage collections and run semantic, metadata, and full-text search over a Chroma vector database.
Pinecone
Pinecone
Pinecone's official developer MCP server: search indexes, manage records, rerank results, and look up Pinecone docs from your agent.
Weaviate
Weaviate
Weaviate's built-in MCP server: hybrid vector and keyword search, schema inspection, and object upserts against a Weaviate vector database.
Milvus
Zilliz
Zilliz's official Milvus MCP server: vector, full-text, and hybrid search plus collection management over a Milvus vector database.
turbopuffer
turbopuffer
turbopuffer's official MCP server helps an agent build on turbopuffer: search the docs and run TypeScript SDK code against your namespaces in a sandbox.