"Hybrid Memory Models Combining Relational, Graph, and RAG Approaches" matching MCP servers:

An MCP server that provides a search_docs tool with hybrid retrieval (BM25 + dense vectors) and cross-encoder reranking, backed by evaluation, prompt-injection guardrails, and OpenTelemetry tracing.

MCP server that lists available GitHub Models and compares responses from multiple models for the same prompt.

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 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.

Exposes a Neo4j knowledge-graph index over personal markdown notes to LLM agents via MCP, enabling semantic search, tag navigation, and relationship discovery.

Graph-based tool retrieval for LLM agents. Builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy from 12% to 82% with 79% fewer tokens. Also works as an MCP Proxy to aggregate multiple servers behind 3 meta-tools.

Exposes a dependency graph of strategic sourcing artifacts and analyses as an MCP server, enabling navigation of phases, analyses, deliverables, and graph traversal for impact analysis and build order.

Enables triage of SAST findings by exposing a read-only MCP server with tools to access hash-verified source-to-sink code slices, unguarded sinks, and layered enrichment for local LLM analysis.

An MCP server that wraps the @apitomy/data-models library for querying, validating, and editing OpenAPI and AsyncAPI documents.

A lean, local knowledge graph that joins a repo's code to its aSPARK delivery artifacts, enabling agents to trace user stories to code and assess impact of changes, served over MCP.

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

Embedded, local-first agent memory: facts extracted into a per-namespace SQLite file (vec0 + FTS5) with hybrid retrieval and point-in-time (time-travel) queries. ADD-only history over stdio — no server process, no cloud dependency.

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 providing persistent memory for AI applications, enabling Claude to store and recall memories with hybrid search and knowledge graph.

MCP server for querying the SEC Ownership Graph, providing curated read-only tools to analyze activist campaigns, control chains, and board interlocks from SEC filings. Answers cite accession numbers and abstain when data is insufficient.

Structural graph map of any codebase. Scans entities, relationships, and feature flows across 13 languages so LLMs navigate by structure instead of reading everything.

Relays a result screenshot to Slack so you can review a coding agent's output without opening the app.

Enables LLMs to inspect database schemas and seed relational databases with custom data while automatically resolving foreign key relationships.

Local-first agent memory & knowledge service: hybrid retrieval (vector + BM25/RRF) + memory governance (decay, dedup, freshness), REST + MCP dual protocol, fully offline without LLM. Python.