AI, Memory & Reasoning MCP Servers

MCP servers that give assistants persistent memory, knowledge graphs and structured reasoning. Each entry is scanned with the deterministic Capability-Flow Trust Model — grades are computed, never self-reported.

Reponova Source verified npm
A
reponova

Knowledge graph builder & MCP server for AI code assistants: search, impact analysis, semantic similarity, and architecture visualization

AI, Memory & Reasoning Score 94/100 1 finding 150/wk Cap. High
Mindforge Source verified npm
A
mindforge-mcp-server

MindForge MCP server — exposes the MindForge engine (knowledge graph, project health, audit log) to Claude Code and any MCP host as 7 stdio tools. Self-contained, zero runtime dependencies.

AI, Memory & Reasoning Score 94/100 2 findings 146/wk Cap. High
Xmemo Client Source verified npm
A
@xmemo/client

Privacy-first CLI and MCP setup helper for XMemo.

AI, Memory & Reasoning Score 94/100 2 findings 142/wk Cap. High
Iranti Source verified npm
A
iranti

Memory infrastructure for multi-agent AI systems

AI, Memory & Reasoning Score 94/100 12 findings 141/wk Cap. High
Velixar Source verified npm
A
velixar-mcp-server

MCP server for Velixar persistent cognitive context — memory, identity, graph, time, and contradiction for LLMs

AI, Memory & Reasoning Score 94/100 2 findings 128/wk Cap. High
Chatcrystal Source verified npm
A
chatcrystal

Local-first AI PKM for coding conversations — supports Claude Code, Cursor, Codex CLI, Trae, GitHub Copilot

AI, Memory & Reasoning Score 94/100 5 findings 121/wk Cap. High
Ccrecall Source verified npm
A
@tznthou/ccrecall

AI memory service for Claude Code — on-demand context injection with metacognition

AI, Memory & Reasoning Score 94/100 1 finding 114/wk Cap. High
Memory Journal Source verified npm
A
memory-journal-mcp

Project context management for AI-assisted development - Persistent knowledge graphs and intelligent context recall across fragmented AI threads

AI, Memory & Reasoning Score 94/100 3 findings 112/wk Cap. High
Nautli Source verified npm
A
nautli

One local brain for all your AI agents. Facts in, contradictions resolved, junk forgotten. While you sleep.

AI, Memory & Reasoning Score 94/100 11 findings 89/wk Cap. High
Bear Notes Source verified npm
A
bear-notes-mcp

Opinionated MCP for Bear Notes. Relevance-ranked search across titles, bodies, hierarchical tags. Offline-first.

AI, Memory & Reasoning Score 94/100 1 finding 88/wk Cap. High
Membot Source verified npm
A
membot

Versioned context store with hybrid search for AI agents. Stdio + HTTP MCP server and CLI.

AI, Memory & Reasoning Score 94/100 2 findings 85/wk Cap. High
Formulon Source verified npm
A
@libraz/formulon-mcp

MCP server for Formulon Excel-compatible formula and workbook evaluation

AI, Memory & Reasoning Score 94/100 3 findings 83/wk Cap. High
Repomemory Source verified npm
A
repomemory

Your codebase never forgets. Persistent, structured memory for AI coding agents.

AI, Memory & Reasoning Score 94/100 4 findings 80/wk Cap. High
Memini Source verified npm
A
memini

Never the same mistake twice — mistake-prevention guardrails and persistent project memory for AI coding agents (Claude Code, Cursor, Windsurf).

AI, Memory & Reasoning Score 94/100 2 findings 79/wk Cap. High
Moldsim npm
A
moldsim-mcp

MCP server for injection molding simulation knowledge — material properties, process validation, troubleshooting, and simulation spec generation

AI, Memory & Reasoning Score 94/100 1 finding 75/wk Cap. Minimal
Qdrant Source verified npm
A
@mhalder/qdrant-mcp-server

MCP server for semantic search using local Qdrant and Ollama (default) with support for OpenAI, Cohere, and Voyage AI

AI, Memory & Reasoning Score 94/100 8 findings 72/wk Cap. High
Thoth Mem Source verified npm
A
thoth-mem

Persistent memory MCP server for AI coding agents

AI, Memory & Reasoning Score 94/100 7 findings 65/wk Cap. High
Genudo Mcp Client Source verified npm
A
genudo-mcp-client

Connect Claude to Genudo — the platform to build AI agents for any communication or sequence-based channel. Create and manage pipeline-aware agents with integrations and company-knowledge access, from one platform, one inbox, and one analytics dashboard.

AI, Memory & Reasoning Score 94/100 1 finding 62/wk Cap. High
Factsets Source verified npm
A
factsets

An MCP server that provides a local, persistent, self-maintaining knowledge base for AI agents

AI, Memory & Reasoning Score 94/100 7 findings 58/wk Cap. High
Elvatis Source verified npm
A
@elvatis_com/elvatis-mcp

MCP server for OpenClaw — expose smart home, memory, cron, and more to Claude Desktop, Cursor, Windsurf, and any MCP client

AI, Memory & Reasoning Score 94/100 4 findings 52/wk Cap. High
Conversation Handoff Source verified npm
A
conversation-handoff-mcp

MCP server for conversation handoff between AI chats/projects

AI, Memory & Reasoning Score 94/100 1 finding 49/wk Cap. High
Cortex Engine Source verified npm
A
@fozikio/cortex-engine

Portable cognitive engine for AI agents — storage, embeddings, memory, FSRS, and MCP server

AI, Memory & Reasoning Score 94/100 6 findings 37/wk Cap. High
Friday Ai Codes Source verified npm
A
@friday-ai-codes/mcp

Friday AI MCP server — expose Friday code intelligence, Graph RAG, coding plan and MR tools to Cursor / Claude Code / Codex via Model Context Protocol

AI, Memory & Reasoning Score 94/100 1 finding 27/wk Cap. High
Vault Memory Source verified npm
A
@owrede/vault-memory

Local-first semantic memory MCP server for Obsidian vaults

AI, Memory & Reasoning Score 94/100 2 findings 27/wk Cap. High