"Logs of user or system queries" matching MCP servers:

Enables real-time auditing of LLM long-term memory to detect contradictions, user-introduced falsehoods, staleness, and unsourced fabrications, while providing a safe memory store with tools like recall, review, and restore.

A scientific reasoning framework that leverages graph structures and the Model Context Protocol (MCP) to process complex scientific queries through an Advanced Scientific Reasoning Graph-of-Thoughts (ASR-GoT) approach.

Enables MCP-capable agents to retrieve relevant slices of a user-story knowledge graph (stored in Supabase + pgvector) using three retrieval verbs: find_related, find_crossover, and query_stories.

Provides versioned, structured memory for AI agents, allowing them to store facts, detect conflicts, and track knowledge history via a hosted SaaS platform. It enables efficient hierarchical information retrieval and semantic search while keeping token usage constant as memory scales.

Gives AI assistants a persistent memory across conversations, allowing them to remember user preferences, notes, and facts between chats.

A powerful context management system that maintains persistent context across coding sessions, helping development teams track project structure, dependencies, and progress.

An MCP server for managing contextual data as markdown files with metadata, enabling agents to save, retrieve, search, and delete contexts using simple CRUD operations.

An improved implementation of persistent memory using a local knowledge graph with a customizable --memory-path. This lets Claude remember information about the user across chats.

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, updating, and scheduling these memories.

Multi-user, file-backed MCP memory server enabling isolated namespaces and persistent memory across sessions and AI clients.

Provides MCP tools to read, write, append, and edit prose sections of nodes, backed by an in-memory or substrate-direct (Urania) backend.

Memory vaults on your own machine, one per life domain, retrieved with a local BM25 index fused with vector search, where the human decides which vaults a model may answer from. Requires the Mnemosyne OS desktop app running locally; it also reports what other coding agents on the same machine are doing.

Provides brain-inspired long-term memory for MCP clients, enabling persistent user understanding across sessions with Chinese-optimized hybrid retrieval and evolving user profiles.

Provides a searchable knowledge base over the Entra.news archive, enabling natural language queries for Microsoft Entra announcements, features, and community tools. Users can perform hybrid semantic searches, retrieve specific newsletter issues, and discover mentioned GitHub projects or PowerShell tools.

MCP server that indexes a knowledge base of past bugs and fixes, making them searchable via BM25 from Claude Code or any MCP client.

Stops AI agents reopening rejected decisions and forgetting project state. Persistent operational state for agents: decisions, plans, blockers, priorities and patterns that survive across sessions, with enforcement. Not conversation logs.

A personal memory MCP server that ingests AI agent conversation logs from multiple platforms into a searchable PostgreSQL+pgvector database, enabling cross-session recall of past reasoning and decisions.

MCP server that provides search and retrieval of AI system failure modes from the Fail Modes taxonomy, covering factuality, alignment, planning, and more.

Hierarchical markdown-based memory system for AI agents. Enables efficient context management by loading only relevant rooms (directories) instead of full memory.

Provenance tree for work: every node knows which node it was born from