Vector Search

Local, token-budgeted code context with file:line provenance and selection receipts.

MCP server exposing PaperQA2 for deep synthesis across scientific papers

Read, search and fill PDFs as markdown, text, tables, forms. Your documents stay on your machine.

Model Context Protocol server exposing openstax-llm pedagogical textbook chunking

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

RETIRED — OpenRAG MCP is now built into the OpenRAG backend as a streamable-HTTP endpoint at /mcp. See README for migration.

Production-ready MCP memory server with semantic search, project conventions learning, and comprehensive memory management for OpenCode

Memory database for LLM agents — persistent semantic + keyword memory, project namespacing, served o

General-purpose RAG MCP plugin — index anything, search with hybrid BM25+semantic, zero-config

MCP server bridging Claude with Google Gemini (video, music, voice, images, Deep Research, agents, 1M context) and 400+ OpenRouter models

MCP server for accessing Ollama models on a remote GPU server via Model Context Protocol

MCP server exposing graph-native code context, document retrieval, schema ranking, document store, cache, and agent pipeline tools.

MCP server that lets any agent query a remote oG-Memory knowledge base with just OGMEM_API_URL + OGMEM_API_TOKEN

Shared memory MCP server — persistent, searchable, cross-client

Local-first document MCP for AI agents: create, read, secure and sign PDF/Word/Excel/PPTX.

Semantic search for Obsidian vaults via MCP

MCP Server for searching Obsidian notes via vector similarity

MCP server that gives AI coding agents accurate NXOpen .NET API knowledge via hybrid retrieval

Subpackage for MCP client integration in NeMo Agent Toolkit

Semantic knowledge engine for Obsidian with auto-classification and DAG hierarchy