"Ram" matching MCP servers:

Unified MCP server: hybrid search + code graph + semantic memory. 10 tools, <350MB RAM, fully local. No API keys.

MCP server for QuelLLM: recommends the best open-source LLM to run locally for your hardware (GPU/RAM), with model comparison and a cost calculator.

Local RAG system for Claude Code with hybrid search (semantic + BM25), cross-encoder reranking, markdown-aware chunking, and 12 MCP tools. Zero external servers, pure ONNX in-process.

Enables searching and reading AWS knowledge from sources the official AWS Knowledge MCP Server does not index, including re:Post community Q&A, kiro.dev documentation, and AWS Builder Center posts.

Exposes hybrid retrieval (dense embeddings + BM25 + RRF) and document operations (search, fetch, rerank) as MCP tools, using Qdrant and OpenAI embeddings for local or server mode.

MCP server that integrates with LM Studio to provide a search_notes tool, allowing the chat model to retrieve and answer from a local Obsidian vault.

Helps AI assistants optimize Linux workloads on Arm64 by parsing perf report output, recommending NEON SIMD intrinsics for hot loops, and auditing Python dependency manifests for arm64 wheel availability — all offline and structured.

A multi-agent Retrieval-Augmented Generation system exposed as an MCP server. Ask a question and a LangGraph pipeline plans the retrieval, pulls evidence from a pgvector knowledge base, optionally augments it with live web research, drafts a cited answer, and then self-critiques it for grounding — revising until the answer is supported by the sources.

A local MCP server that enables LLMs to securely search and read files within designated Google Drive folders. Supports Google Docs, Google Sheets, PDFs, and plain text with strict folder-scoping via service account authentication.

MCP server that integrates Apache Ranger authorization with RAG, enforcing Ranger policies to control access to knowledge bases before forwarding queries to RAG Studio.

Enables indexing local documents (PDF, Markdown, text, code) into a knowledge base and querying them via semantic search using local embeddings, all running privately on your machine.

MCP server that enables AI agents to search the entire TouchDesigner wiki documentation with real citations, using a local index built from the official wiki.

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

Enables MCP-capable agents to query a LightRAG knowledge graph for grounded answers with source files, ingest documents into the index, and retrieve indexing statistics.

Enables local-first hybrid knowledge retrieval from authorized Markdown and plain-text files, combining full-text and vector search with reranking and traceable source references via a single search tool.

A self-hosted MCP server that fetches live documentation and performs code audits using real-time authoritative references to prevent AI hallucinations. It provides tools for searching documentation across 330+ libraries and scanning local source code for security, performance, and accessibility issues.

A hosted multimodal RAG MCP server that enables natural language queries over text and visual content (PDFs, images, etc.) with verifiable citations, easily run via npx with a Calypso API key.

Enables MCP-compatible AI clients to securely monitor and manage a self-hosted Linux VPS over SSH, including service status, disk and RAM usage, TLS certificate expiry, fail2ban summaries, and two-step confirmed service restarts or IP unbans.

Pulls enterprise counts by NACE Rev.2 activity and size class from Eurostat and buckets them into SME and 250+ categories for the DTM TAM model, with tools to fill TAM spreadsheets directly.

Provides retrieval and analysis tools for a quantitative-finance research library, enabling whole-passage answers with verifiable citations, citation checking, entity graph exploration, and corpus inspection.