RAG & Vector Search MCP Servers

MCP servers matching "RAG & Vector Search" by name or description — 147 MCP servers, ranked by GitHub stars.

R

ReftrixMCP

Development

Web design analysis with 26 MCP tools: layout, motion, quality, semantic search via pgvector

★ 2 MCP Server
R

retrieval-lens

Development

Black-box flight recorder for RAG retrieval inside MCP agents. Logs chunks, scores, sources and rankings so you can audit, replay and diff…

★ 2 MCP Server
A

Alexandria-mcp

Design & Media

Semantic search over 4.6 million text chunks from 20,000 classical philosophy and humanities works. Built for AI agents using FastMCP.

★ 1 MCP Server
F

Food-Recipe-MCP

Other

Semantic search across 50,000+ food recipes with hybrid retrieval and reranking.

★ 1 MCP Server Reachable
M

memex

Knowledge & Memory

Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.

★ 1 MCP Server
F

FlexOrch

Databases & Data

Classify documents, extract structured fields, mask PII, export JSONL/RAG datasets for AI agents.

★ 1 MCP Server
M

md-vision

Knowledge & Memory

Read markdown with inlined images and index headings for agentic RAG workflows.

★ 1 MCP Server
K

k402-mcp

Finance

Agent-payable APIs settled on Kaspa L1: text tools (summarize, schema-guaranteed extract, classify, rewrite), web reading, embeddings +…

★ 1 MCP Server
M

mcp-roo-memory

Knowledge & Memory

Persistent fractal graph memory for AI coding agents via MCP. Semantic vector search, hot/cold/archive context tiers, decision tracking,…

★ 1 MCP Server
B

bitcoinbenji-mcp

Finance

Lightning-paid (L402) Bitcoin mempool intelligence + sovereign on-prem AI inference. 25 pay-per-call tools: live fees with trend,…

★ 1 MCP Server
F

forge-mcp

Search & Research
Official

MCP server for Forge, Voxell's hosted text-embedding API. Tools: embed and list_models.

★ 1 MCP Server
M

memory-nexus-cloud

Knowledge & Memory

Cloud-hosted persistent semantic memory for AI agents. Semantic search, knowledge graphs, specialist expertise hats, and multi-tenant…

MCP Server
Z

zipmem-mcp

Knowledge & Memory

Local-first long-term memory for terminal AI agents (Claude Code et al.) via Anchored Compacting. Stores blueprints, code anchors…

MCP Server
E

engram-mcp

Knowledge & Memory

Persistent semantic memory for AI agents. SQLite-backed, local-first, zero config. Semantic search via Ollama embeddings…

MCP Server
C

conformi-search-mcp

Productivity

EU legal research with verifiable CELEX citations from the EUR-Lex corpus (DE/EN/FR). Semantic search, knowledge reports and…

MCP Server
A

agentic-recall

Knowledge & Memory

Long-term memory across sessions over a folder of plain markdown files. Hybrid retrieval (BM25F + dense vectors + phrase proximity) with…

MCP Server
R

rag-mcp

Knowledge & Memory

Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.

MCP Server
I

Idencify

Development
Official

Whole-repo code graph for AI agents: impact analysis, dead code, cycles, semantic search — 14 tools.

MCP Server
N

Novyx MCP

Knowledge & Memory

Persistent memory for AI agents with rollback, audit trails, and semantic search.

MCP Server
P

Pexafy

Search & Research

Semantic search over free-to-use stock photos from 9 libraries: by words, image, or similar.

MCP Server Requires auth
O

opensolr-mcp

Search & Research

Managed Apache Solr for agents: hybrid BM25+kNN search, server-side embeddings, RAG answers

MCP Server
C

cloudflare-workers-ai-mcp

Communication

Cloudflare Workers AI inference for AI agents: LLM chat completions (Llama 3.3 70B, Llama 3.1 8B, Llama 4 Scout, Qwen Coder 32B, DeepSeek…

MCP Server
M

mem-context

Knowledge & Memory

Temporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation

MCP Server
V

vpuna-ai-search

Search & Research
Official

Connect to [Vpuna AI Search Service](https://aisearch.vpuna.com), a developer first platform for semantic search, summarization, and…

MCP Server
C

ckg-mcp

Knowledge & Memory

97-domain knowledge graphs for AI agents — 4× F1 of RAG, 11× fewer tokens. MCP-native.

MCP Server
S

story-cli

Knowledge & Memory

Git-native Markdown content management CLI with built-in MCP Server. Search, read, write, and govern story/paper/note repositories;…

MCP Server
A

ai·rete·rag

Search & Research

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.

MCP Server Reachable