Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
rag-knowledge-graph-mcp
MCP serversRag Knowledge Graph MCP Server by MEOK AI Labs
rag-knowledge-graph-mcp@1.0.8 -
Ragora
MCP serversSearch your knowledge bases from any AI assistant using hybrid RAG.
-
ragnarok
MCP serversLocal RAG search over Obsidian vaults: SQLite hybrid search with local Ollama embeddings.
ragnarok-mcp@2.3.0 -
google-surf-mcp
MCP serversWeb, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.
google-surf-mcp@1.1.6 -
ragmetric-mcp
MCP serversRAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch.
@mukundakatta/ragmetric-mcp@0.1.1 -
rag
MCP serversMCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.
FieldCure.Mcp.Rag@2.5.1 -
RAGbase Shield
MCP serversLocal, reversible pseudonymisation of client files for Claude, ChatGPT and Copilot.
ragbase-shield@0.4.0 -
rag-vault
MCP serversLocal RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
@robthepcguy/rag-vault@1.5.3 -
rag-mcp
MCP serversMinimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.
jaimenbell-rag-mcp@0.1.0 -
Linggen - Local RAG
MCP serversLocal, privacy-focused RAG service for code search via MCP. https://linggen.dev
-
agenticos
MCP serversOpen-source, self-hosted AI agent platform for your company's AI teammates. Build, run and govern agents on your own servers and models: shared chat, RAG, skills, a real browser, 4,700+ MCP servers, budgets, approvals and an audit trail. An alternative to ChatGPT Enterprise and Grok Bot. Apache-2.0, built on Pydantic AI.
git clone https://github.com/vstorm-co/agenticos.git -
awesome-agent-memory
MCP serversA curated list of memory systems, frameworks, benchmarks, and research for AI agents.
git clone https://github.com/mnemoverse/awesome-agent-memory.git -
Calypso Multimodal RAG MCP
MCP serversCalypso multimodal RAG for grounded answers from docs, images, charts, and knowledge.
@calypsohq/multimodal-rag-mcp-server@3.0.0 -
mcp-knowledge-rag
MCP serversPermission-aware RAG for agents — ingest docs, hybrid search, cited answers (hosted API).
@infoinlet/mcp-knowledge-rag@0.1.0 -
mem-forge
MCP serversGive every agent your team's brain on day one. The memory layer for AI agents. Everything your team knows. Cited, and always up to date.
git clone https://github.com/dodo-labs-ai/mem-forge.git -
all2md
MCP serversConvert PDF, Word, PowerPoint, HTML, email & 40+ formats to clean Markdown — and back. Built for LLMs, RAG & Python pipelines, with a built-in MCP server.
git clone https://github.com/thomas-villani/all2md.git -
rag-service-mcp
MCP serversRAG-as-a-service MCP sunucusu — çok-kiracılı koleksiyon yönetimi, metin ingest (chunk+embed+upsert,…
-
cob-rag-mcp
MCP serversGive any MCP client a business's own knowledge base from a self-hosted cob-rag-engine.
cob-rag-mcp@0.2.0 -
rag-embedding-poisoning-escrow-auditor
MCP serversERC-8183 RAG Knowledge Base & Vector Embedding Anti-Poisoning Auditor & Escrow on Base.
-
datasinking
MCP serversFull-text financial reports (US, China, Japan, Korea, Taiwan) as clean Markdown — REST API + MCP server for LLMs, RAG and quant
git clone https://github.com/heubme2020/datasinking.git -
anymd
MCP serversAny file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
git clone https://github.com/SylphxAI/anymd.git -
Document to Markdown for LLM & RAG
MCP serversPDF, Word, PowerPoint and scans to Markdown or RAG chunks, via the Apify actor
-
Rag retrieval evaluation tuning — Atom
MCP serversRag retrieval evaluation tuning, delivered per API call as an atom service on Conduit Atoms.
-
URL to Clean Markdown for LLMs & RAG
MCP serversFetch URLs and return clean Markdown for RAG — nav, ads and boilerplate stripped.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.