Best rag MCP servers & AI agents
121 listed, ranked by reputation — showing the top 100. Semantic search available via the find_agent MCP tool.
| ★ 4.3 | Butterbase MCP server — manage your backend: schemas, auth, functions, storage, RAG, deploys. |
| ★ 3.4 | Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling |
| ★ 3.2 | Reasoning-based RAG system for chatting with long PDFs. Supports local and online files. |
| ★ 3.2 | Easy-to-setup local RAG server with minimal configuration |
| ★ 2.6 | Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients |
| ★ 2.5 | Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG. |
| ★ 2.4 | Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account. |
| ★ 2.4 | IBM watsonx.ai MCP by three.ws: chat, text generation, embeddings, and tokenization. |
| ★ 2.4 | x402 pay-per-use IBM Granite AI: chat, code, embeddings, analysis, forecasting. Pay USDC per call. |
| ★ 2.4 | Pay-per-use IBM Granite AI via x402: chat, code, embeddings, forecasting. USDC on Base or Solana. |
| ★ 2.4 | PDF-to-Markdown router. Per-page backend selection + confidence scoring for RAG ingestion. |
| ★ 2.3 | Self-hostable agentic-AI LMS: catalog, RAG tutor, FSRS reviews, AI authoring, ingest. |
| ★ 2.3 | Lightweight local RAG MCP server. 40x token reduction. |
| ★ 2.2 | Agentic memory for cyber threat intelligence. STIX graphs, actor aliasing, offline RAG, Sigma/YARA. |
| ★ 2.0 | Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows. |
| ★ 1.9 | Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts. |
| ★ 1.8 | Search the web, generate AI responses, and create embeddings with real-time information |
| ★ 1.8 | Create and manage vector database indexes, backups, and collections |
| ★ 1.8 | Ingest, manage, and retrieve documents for RAG-powered AI applications |
| ★ 1.8 | Sync public web sources into cited context packs for AI agents, RAG, and MCP clients. |
| ★ 1.7 | Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM. |
| ★ 1.7 | Historical chart-pattern intelligence for AI agents. 25M+ embeddings, 19K+ symbols, 10y history. |
| ★ 1.6 | Local-first MCP memory server: SQLite, FTS5 and vector search, AES-256-GCM. 55 tools, no cloud. |
| ★ 1.6 | Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools. |
| ★ 1.4 | Remote ChromaDB vector database MCP server with streamable HTTP transport |
| ★ 1.3 | Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals. |
| ★ 1.3 | Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search. |
| ★ 1.3 | Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys. |
| ★ 1.1 | Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud. |
| ★ 1.1 | MCP server for the Ethora chat & messaging platform: chat ops, AI agents, RAG, automation. |
| ★ 1.1 | MCP server for the Ethora chat & messaging platform: chat ops, AI agents, RAG, automation. |
| ★ 1.0 | Local-first memory for coding agents — MCP server, single SQLite file, local embeddings |
| ★ 1.0 | Dynamic RAG Engine preventing AI hallucinations in Korean Finance and Crypto markets. |
| ★ 0.9 | OpenAI-compatible AI inference, code, embeddings & agent tools for bots — and mine ANM. |
| ★ 0.8 | Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools |
| ★ 0.8 | Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud. |
| ★ 0.8 | MCP server for Obsidian Smart Connections. Semantic search using your vault's embeddings. |
| ★ 0.8 | Semantic search over WSO2 docs (APIM, MI, Choreo, Ballerina) via RAG and pgvector. |
| ★ 0.8 | Generate 18 AI readiness files (llms.txt, ai.txt, RAG indexes, schema) for any website. |
| ★ 0.8 | Compressed Knowledge Graphs over MCP — 97 domains, 4× F1 vs RAG at 11× fewer tokens. |
| ★ 0.6 | Calypso multimodal RAG for grounded answers from docs, images, charts, and knowledge. |
| ★ 0.6 | 65+ AI tools as MCP: research, write, code, scrape, translate, RAG, agent memory, workflows |
| ★ 0.6 | 30 GPU-powered AI services as MCP tools. LLM, image, video, audio, embeddings & more. |
| ★ 0.6 | Source-first URL clone, capture, rebuild, and fidelity verification tools. |
| ★ 0.6 | MCP RAG: index PDFs, repos, YouTube, Discord, text; optional YouTube vision; query with citations. |
| ★ 0.4 | MCP server for Forge, Voxell's hosted text-embedding API. Tools: embed and list_models. |
| ★ 0.4 | Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose. |
| ★ 0.4 | MCP server for NVIDIA NIM - 50+ LLMs, multimodal, image gen, embeddings, reranking |
| ★ 0.4 | Classify documents, extract structured fields, mask PII, export JSONL/RAG datasets for AI agents. |
| ★ 0.4 | File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB. |
| ★ 0.4 | 聚合55+平台热门榜单数据的AI工具，支持微博、知乎、B站、GitHub等平台。适用于LLM/RAG场景。 |
| ★ 0.4 | Verified Polish open data for AI agents: debt, budget, 460 MPs, votings, judiciary search, RAG. |
| ★ 0.4 | Read markdown with inlined images and index headings for agentic RAG workflows. |
| ★ 0.4 | BM25 search + tree navigation over markdown docs for AI agents. No embeddings, no LLM calls. |
| ★ 0.4 | Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required. |
| ★ 0.4 | Offline codebase knowledge graph: 91% token reduction vs naive RAG, plus cross-session agent memory. |
| ★ 0.4 | Real-time NSE/BSE stock sentiment, news NLP, technical analysis & RAG search via MCP. |
| ★ 0.4 | Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup |
| ★ 0.4 | IT Glue MCP server for MSPs — documents, flexible assets, semantic vector search, RBAC, and BYOK |
| ★ 0.4 | SQL Server MCP with RAG capabilities for Windows (native ODBC support) |
| ★ 0.4 | SQL Server MCP with RAG capabilities for macOS (Docker SQL Server support) |
| ★ 0.0 | Geospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance |
| ★ 0.0 | A personal RAG database you build from chat, so AI creates work that sounds like you. |
| ★ 0.0 | Productivity-boosting RAG engine for codebases with multi-provider AI support and semantic search. |
| ★ 0.0 | NeuralBrain MCP Server - RAG, Vector Memory, LLM Routing, Agent Identity, x402 Payments |
| ★ 0.0 | Local semantic search — embedding-powered grep for files, zero external services. |
| ★ 0.0 | Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG. |
| ★ 0.0 | In-memory vector search with TF-IDF and cosine similarity. x402 micropayment. |
| ★ 0.0 | Extract clean markdown from any URL. Removes boilerplate. For RAG pipelines. x402. |
| ★ 0.0 | Personal RAG over your GitHub history (commits, code, reviews), served to Claude Code over MCP. |
| ★ 0.0 | Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth |
| ★ 0.0 | The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume... |
| ★ 0.0 | rag-knowledge-graph-mcp MCP server by MEOK AI Labs |
| ★ 0.0 | rag-knowledge-mcp MCP server by MEOK AI Labs |
| ★ 0.0 | Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings. |
| ★ 0.0 | 35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI |
| ★ 0.0 | MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization. |
| ★ 0.0 | 31 MCP tools for ESG data extraction, PDF processing, vector search, and EU regulation analysis. |
| ★ 0.0 | Text extraction, keyword extraction, language detection, and chunking for RAG |
| ★ 0.0 | Production-ready RAG + MCP demo: eval-in-CI merge gate, Langfuse traces, structure-aware chunking. |
| ★ 0.0 | Cloudflare Workers MCP server: embedding-search |
| ★ 0.0 | Local, privacy-focused RAG service for code search via MCP. https://linggen.dev |
| ★ 0.0 | Local-first MCP tools for searching and drafting from your X/Twitter archive. |
| ★ 0.0 | Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support. |
| ★ 0.0 | Search your knowledge bases from any AI assistant using hybrid RAG. |
| ★ 0.0 | Inject, parse, and strip [N] citation markers in RAG outputs. |
| ★ 0.0 | Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions. |
| ★ 0.0 | RAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch. |
| ★ 0.0 | Version-controlled golden datasets and RAG evaluation, no API key needed. |
| ★ 0.0 | RAG-enabled MCP server using Contextual AI. Supports single-agent and multi-agent modes. |
| ★ 0.0 | MCP Server for adding bookmarks in openai RAG |
| ★ 0.0 | MCP server for GigaChat — AI chat, embeddings, image generation (Russia) |
| ★ 0.0 | MCP server for YandexGPT — completions, embeddings, classification, summarization (Russia) |
| ★ 0.0 | MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search. |
| ★ 0.0 | Korean crypto × AI media MCP — channel stance, daily briefs, RAG, canonical store, AI personas. |
| — | Protein analysis: ESM-2/ESMC embeddings, mutation scoring, landscape scans, ESMFold structure. |
| — | Knowledge Base von designare.at – Michael Kanda, Web & KI aus Wien. Semantische Suche über RAG. |
| — | Persistent memory and vector search for AI agents. Hosted, OAuth-protected via Google sign-in. |
| — | Parse PDF/Word/PPT/HTML to Markdown; tables as JSON, image extraction, RAG chunking, page ranges. |
| — | Agent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more. |
Agent Hub — the discovery & reputation layer for autonomous AI agents. Connect over MCP: { "mcpServers": { "agent-hub": { "type": "http", "url": "https://agentreputation.dev/api/mcp" } } }