MCP servers for vector & semantic search
Store and query embeddings for RAG and long-term agent memory.
13 servers · Last updated August 1, 2026
TL;DR: These servers give your agent a vector store — upserting embeddings and running similarity search for RAG and persistent memory. They differ on whether they're a dedicated vector DB, a general database with vector support, or an in-process memory store. This is the retrieval half of any RAG stack.
Bottom line: if you only try one, Memory (Knowledge Graph) is the most popular, verified option for this (74,000★). 12 more compared below.
Compare 13 servers
| Server | Transport | Auth | Verified | Stars | Tools for this |
|---|---|---|---|---|---|
| Memory (Knowledge Graph) | Local (stdio) | No auth | 74,000 | create_entities, delete_entities, read_graph +2 | |
| OpenMemory MCP | Remote (SSE) | API key | — | 59,874 | search_memory |
| Graphiti MCP | Remote (HTTP) | API key | — | 28,240 | add_memory, search_nodes, search_memory_facts +2 |
| MCP Server Chart | Local (stdio) | No auth | — | 4,169 | generate_network_graph |
| Qdrant MCP Server | Local (stdio) | API key | 1,100 | qdrant-store, qdrant-find | |
| Mem0 MCP Server | Local (stdio) | API key | — | 655 | add_memory, get_memory, update_memory +3 |
| Chroma MCP Server | Local (stdio) | API key | 600 | chroma_list_collections, chroma_create_collection, chroma_peek_collection +4 | |
| dbt MCP Server | Local (stdio) | API key | — | 584 | get_entities, get_semantic_model_details |
| Pinecone Developer MCP Server | Local (stdio) | API key | 500 | upsert-records, search-records | |
| Graphlit MCP Server | Local (stdio) | API key | — | 375 | Query Collections, Ingest Memory (Short-Term), Collection Operations |
| MCP ECharts | Local (stdio) | No auth | — | 242 | generate_graph_chart |
| ChatSpatial | Local (stdio) | No auth | — | 40 | compute_embeddings |
| ENCODE Toolkit | Local (stdio) | No auth | — | 35 | encode_summarize_collection |
The servers
Official MCP server providing persistent, file-backed knowledge-graph memory across sessions.
Mem0's local-first memory layer: a Dockerized MCP server plus dashboard that keeps agent memories on your machine.
Temporal knowledge-graph memory for agents: add episodes and search facts over FalkorDB or Neo4j, from Zep.
Generate 26+ chart types and data visualizations using AntV, for chart generation and data analysis.
Official Qdrant server using a vector collection as semantic memory: store and find embeddings.
Archived official Mem0 server for long-term agent memory: add, search, update, and delete memories via the Mem0 API.
Official Chroma server: create collections and run vector, full-text, and metadata search.
Give AI agents context of your dbt project — run dbt CLI, query the Semantic Layer, explore lineage, and manage jobs.
Official Pinecone server: manage indexes, upsert/search records, rerank, and search Pinecone docs.
Ingest, search, and RAG over data from Slack, Discord, Google Drive, GitHub, Jira, Linear and more via Graphlit.
Generate Apache ECharts charts locally from AI for chart generation and data analysis.
MCP server for spatial transcriptomics analysis via natural language
Search ENCODE, cross-reference 14 genomics databases, run analysis pipelines, and generate publication-ready methods from natural language.
Use these in a stack
FAQ
Dedicated vector DB vs memory server?
Use a dedicated vector store (Chroma, Qdrant, Pinecone) for scale and persistence; a lightweight memory server is fine for small, single-agent context.
What pairs with a vector server for RAG?
A scraping/search server to gather content and an embeddings step — see the RAG agent stack for a ready-made combination.