MCP Directory

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

ServerTransportAuthVerifiedStarsTools for this
Memory (Knowledge Graph)Local (stdio)No auth74,000create_entities, delete_entities, read_graph +2
OpenMemory MCPRemote (SSE)API key59,874search_memory
Graphiti MCPRemote (HTTP)API key28,240add_memory, search_nodes, search_memory_facts +2
MCP Server ChartLocal (stdio)No auth4,169generate_network_graph
Qdrant MCP ServerLocal (stdio)API key1,100qdrant-store, qdrant-find
Mem0 MCP ServerLocal (stdio)API key655add_memory, get_memory, update_memory +3
Chroma MCP ServerLocal (stdio)API key600chroma_list_collections, chroma_create_collection, chroma_peek_collection +4
dbt MCP ServerLocal (stdio)API key584get_entities, get_semantic_model_details
Pinecone Developer MCP ServerLocal (stdio)API key500upsert-records, search-records
Graphlit MCP ServerLocal (stdio)API key375Query Collections, Ingest Memory (Short-Term), Collection Operations
MCP EChartsLocal (stdio)No auth242generate_graph_chart
ChatSpatialLocal (stdio)No auth40compute_embeddings
ENCODE ToolkitLocal (stdio)No auth35encode_summarize_collection

The servers

Official MCP server providing persistent, file-backed knowledge-graph memory across sessions.

create_entitiesdelete_entitiesread_graphsearch_nodesopen_nodes

Mem0's local-first memory layer: a Dockerized MCP server plus dashboard that keeps agent memories on your machine.

search_memory

Temporal knowledge-graph memory for agents: add episodes and search facts over FalkorDB or Neo4j, from Zep.

add_memorysearch_nodessearch_memory_factsget_episode_entitiesclear_graph

Generate 26+ chart types and data visualizations using AntV, for chart generation and data analysis.

generate_network_graph

Official Qdrant server using a vector collection as semantic memory: store and find embeddings.

qdrant-storeqdrant-find

Archived official Mem0 server for long-term agent memory: add, search, update, and delete memories via the Mem0 API.

add_memoryget_memoryupdate_memorydelete_memorydelete_entitieslist_entities

Official Chroma server: create collections and run vector, full-text, and metadata search.

chroma_list_collectionschroma_create_collectionchroma_peek_collectionchroma_get_collection_infochroma_get_collection_countchroma_modify_collection

Give AI agents context of your dbt project — run dbt CLI, query the Semantic Layer, explore lineage, and manage jobs.

get_entitiesget_semantic_model_details

Official Pinecone server: manage indexes, upsert/search records, rerank, and search Pinecone docs.

upsert-recordssearch-records

Ingest, search, and RAG over data from Slack, Discord, Google Drive, GitHub, Jira, Linear and more via Graphlit.

Query CollectionsIngest Memory (Short-Term)Collection Operations

Generate Apache ECharts charts locally from AI for chart generation and data analysis.

generate_graph_chart

MCP server for spatial transcriptomics analysis via natural language

compute_embeddings

Search ENCODE, cross-reference 14 genomics databases, run analysis pipelines, and generate publication-ready methods from natural language.

encode_summarize_collection

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.

Other capabilities