Best Vector Search MCP Servers

Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.

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

Markdown vault MCP server with FTS5 + semantic search and frontmatter indexing

Advanced codebase indexing and semantic search MCP server

Read-only semantic search over Vedic scripture verses, commentaries, and recorded lectures.

Semantic search over MINDSET's brand strategy topic database, plus its system prompt.

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

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

Semantic search for Historical Soundscapes. Search eventos, entities, filters. Cross-lingual ES/EN.

Universal MCP Server with advanced AI memory capabilities and semantic search.

Ingest, manage, and retrieve documents for RAG-powered AI applications

MCP server for converting bitmap images to SVG vector graphics using potrace tracing.

QR & barcode toolkit: generate, decode, vector SVG, logo QR, WiFi and vCard QR codes.

Real-time product data, semantic search and more from dm-drogerie markt, Europe's leading drugstore.

rag-knowledge-graph-mcp MCP server by MEOK AI Labs

AI tools for agents: chat, summarize, classify, entity extraction, embeddings, transcription. x402

Local-first memory for coding agents — MCP server, single SQLite file, local embeddings

Local semantic search — embedding-powered grep for files, zero external services.

Semantic search across 6,236 Quran verses and 12,416 authentic Hadiths for Islamic guidance.

Disposable private vector search + semantic RAG for AI agents. x402 pay-per-call, no account.

rag-knowledge-mcp MCP server by MEOK AI Labs

Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings.

GitHub repository vectorizer and context synthesizer for RAG pipelines.

Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens.

Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.

Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search.

Semantic search over IMAGIN.studio API documentation — CDN, API, integration guides, and more.

Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.

Semantic search knowledge base with serverless LanceDB. Zero setup, 100% local, 25+ file types

Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.