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.

Cogmemai npm
B
cogmemai-mcp

CogmemAi: Autonomous Cognitive Memory for Any Ai System. 95.10% on LongMemEval (top published score on the field's hardest long-term memory benchmark) and 91% on LoCoMo (above human performance). Autonomous memory capture: your Ai's work is saved even whe

AI, Memory & Reasoning Score 84/100 6 findings 254/wk Cap. High
Getengram Cli npm
B
@getengram/cli

CLI for Engram — persistent memory for AI agents

AI, Memory & Reasoning Score 84/100 5 findings 55/wk Cap. High
Kernl npm
B
kernl-mcp

KERNL V2.0 - Persistent Intelligence Layer for AI. Transform Claude from stateless to persistent with 75 tools: crash recovery, semantic search, cross-project learning, system control, and 100% Desktop Commander parity.

AI, Memory & Reasoning Score 84/100 6 findings 50/wk Cap. High
Mindkeg Source verified npm
B
mindkeg-mcp

A persistent memory MCP server for AI coding agents — stores, searches, and retrieves atomic learnings per repository.

AI, Memory & Reasoning Score 84/100 4 findings 22/wk Cap. Critical
Vemdev Source verified npm
B
@vemdev/mcp-server

Official VEM MCP Server for AI agent project memory.

AI, Memory & Reasoning Score 84/100 2 findings 20/wk Cap. Critical
Memkin Source verified npm
B
memkin

Local-first personal memory system — extracts signals from Feishu/Lark chats and AI-agent sessions into a private knowledge graph, served to any agent via MCP

AI, Memory & Reasoning Score 84/100 13 findings 17/wk Cap. Critical
Python PyPI
B
python-mcp-server

A world-class Python interpreter MCP server with session management, health monitoring, and FastMCP middleware

AI, Memory & Reasoning Score 84/100 13 findings Cap. High
Mcpize Source verified npm
B
mcpize

Deploy and monetize MCP servers in the cloud

AI, Memory & Reasoning Score 83/100 9 findings 64/wk Cap. High
Personal Kg npm
B
@tomschell/personal-kg-mcp

Personal Knowledge Graph MCP server for maintaining a local, private knowledge graph of decisions, progress, insights, and questions during development

AI, Memory & Reasoning Score 83/100 3 findings 23/wk Cap. Critical
Memoryd npm
B
@enbox/memoryd

User-owned AI memory layer with task graph, built on DWN protocols. MCP server.

AI, Memory & Reasoning Score 83/100 6 findings 18/wk Cap. High
Ragi Source verified npm
B
@susutawar/ragi

Local-first RAG indexing and semantic search MCP server

AI, Memory & Reasoning Score 83/100 6 findings 16/wk Cap. High
Basic Memory PyPI
B
basic-memory

Local-first knowledge base: persistent semantic notes your assistant reads and writes.

AI, Memory & Reasoning Score 83/100 11 findings Cap. Critical
Signal PyPI
B
signal-mcp

Complete Signal MCP server and CLI via signal-cli

AI, Memory & Reasoning Score 83/100 7 findings Cap. High
Mindswap npm
B
mindswap

Your AI's black box recorder. Auto-track project state so any AI tool picks up where the last one stopped.

AI, Memory & Reasoning Score 82/100 9 findings 106/wk Cap. High
Brain npm
B
brain-mcp

Brain MCP Server - Semantic knowledge base access for Claude Code via Model Context Protocol. Provides intelligent search and navigation of files from multiple locations through native MCP tools.

AI, Memory & Reasoning Score 82/100 8 findings 20/wk Cap. High
Graph npm
B
@graph-tl/graph

Agent-native persistent task graph. MCP server for agent planning and execution across sessions.

AI, Memory & Reasoning Score 82/100 7 findings 12/wk Cap. High
FalkorDB Source verified npm
B
@falkordb/mcpserver

Lets AI assistants query and manage FalkorDB graph databases using natural language.

AI, Memory & Reasoning Score 81/100 2 findings 340/wk Cap. Minimal
Midnight npm
B
midnight-mcp

[DEPRECATED — migrate to Kapa + Midnight Expert: https://docs.midnight.network/blog/migrating-to-kapa-and-midnight-expert] Model Context Protocol Server for Midnight Blockchain Development

AI, Memory & Reasoning Score 81/100 2 findings 106/wk Cap. Moderate
Opscontext npm
B
@compr/opscontext-mcp

OpsContext for AI Agents — read-only fleet visibility (PM2/nginx/Docker/git/cron) + tamper-evident audit log + policy-as-code hooks. The ops + compliance layer Claude Code can't grow natively.

AI, Memory & Reasoning Score 80/100 17 findings 126/wk Cap. High
Perp Cli npm
B
perp-cli

Multi-DEX Perpetual Futures CLI - Pacifica, Hyperliquid, Lighter, Aster

AI, Memory & Reasoning Score 80/100 19 findings 52/wk Cap. High
Code npm
B
@axme/code

Persistent memory, decisions, and safety guardrails for Claude Code

AI, Memory & Reasoning Score 80/100 16 findings 31/wk Cap. Critical
Local npm
B
@awareness-sdk/local

Local-first AI agent memory system. No account needed.

AI, Memory & Reasoning Score 80/100 13 findings 20/wk Cap. High
Smriti npm
B
smriti

Local-first persistent memory MCP server for AI agents — with consolidation loop and git sync

AI, Memory & Reasoning Score 80/100 5 findings 16/wk Cap. Critical
Mevoric npm
B
mevoric

Unified memory + agent bridge for Claude Code. Semantic recall, cross-tab messaging, session checkpoints — one MCP server.

AI, Memory & Reasoning Score 80/100 6 findings 13/wk Cap. Critical