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.

Cortex Brain npm
A
cortex-brain

Give your AI agents a company brain. MCP server over a markdown knowledge base: cited articles, freshness tracking, open questions, and a safe inbox write path.

AI, Memory & Reasoning Score 96/100 0 findings 16/wk Cap. Moderate
English Tutor npm
A
english-tutor-mcp

Local MCP server that silently collects your English utterances while you chat with your AI assistant and batch-analyzes them into daily grammar-pattern reports

AI, Memory & Reasoning Score 96/100 0 findings 16/wk Cap. Moderate
Isis npm
A
isis-mcp

MCP Server for web scraping - Apify RAG Web Browser equivalent functionality

AI, Memory & Reasoning Score 96/100 0 findings 16/wk Cap. Moderate
N8n Webhook npm
A
@grec0/mcp-n8n-webhook

MCP server para enviar información a webhook de n8n

AI, Memory & Reasoning Score 96/100 0 findings 16/wk Cap. Moderate
638labs npm
A
@638labs/mcp-server

MCP server for the 638Labs AI agent registry. Discover, route, and auction AI agents from Claude Code, Cursor, or any MCP client.

AI, Memory & Reasoning Score 96/100 0 findings 15/wk Cap. Moderate
Chaosintelligence npm
A
@chaosintelligence/mcp

MCP server for Chaos Intelligence — access your Capture thoughts and Resonate posts from Claude, Cursor, and other AI tools

AI, Memory & Reasoning Score 96/100 0 findings 15/wk Cap. Moderate
Raggy npm
A
raggy-mcp

MCP server for Raggy - universal memory for AI agents. Ships with a built-in agent protocol so every connected client auto-loads the rules for when to capture, recall, link, and forget memories.

AI, Memory & Reasoning Score 96/100 1 finding 15/wk Cap. Moderate
Useconduit npm
A
@useconduit/mcp

MCP server for Conduit — connect any AI agent to your data streams

AI, Memory & Reasoning Score 96/100 0 findings 15/wk Cap. Moderate
Booklab npm
A
booklab-mcp

BookLab by Bjorn — MCP server for nonfiction book recommendations. 10+ years of human-curated reviews, structured for AI agents.

AI, Memory & Reasoning Score 96/100 1 finding 14/wk Cap. Moderate
Dropdat npm
A
@dropdat/mcp

Dropdat MCP server — recall, save, and read AI-chat capsules from any MCP-capable client (Claude Code, Cursor, Cline, Claude Desktop).

AI, Memory & Reasoning Score 96/100 0 findings 14/wk Cap. Moderate
Enhx Memory npm
A
enhx-memory

Lightweight SQLite-based persistent memory MCP server for AI coding agents. A minimal TypeScript implementation — not as heavy as enhanced-mcp-memory (which uses transformers, embeddings, etc).

AI, Memory & Reasoning Score 96/100 0 findings 14/wk Cap. Moderate
Kiro Research npm
A
@thejusdutt/kiro-research-mcp

Claude Research-style MCP server implementing Anthropic's multi-agent research methodology with source quality assessment and iterative searching

AI, Memory & Reasoning Score 96/100 0 findings 14/wk Cap. Moderate
Llmmcp npm
A
llmmcp

MCP server for real-time LLM API documentation — stop hallucinations

AI, Memory & Reasoning Score 96/100 1 finding 14/wk Cap. Moderate
Policy npm
A
@rcrsr/mcp-policy-server

MCP server providing token-efficient access to policy documentation via § notation

AI, Memory & Reasoning Score 96/100 0 findings 14/wk Cap. Moderate
Ragchat npm
A
mcp-ragchat

MCP server that adds RAG-powered AI chat to any website. One command from Claude Code.

AI, Memory & Reasoning Score 96/100 3 findings 14/wk Cap. Moderate
Docmole npm
A
docmole

Dig through any documentation with AI - MCP server for Claude, Cursor, and other AI assistants

AI, Memory & Reasoning Score 96/100 2 findings 13/wk Cap. Moderate
Lumencore npm
A
lumencore

Persistent project memory for AI agents - MCP server for Claude Code

AI, Memory & Reasoning Score 96/100 0 findings 13/wk Cap. Moderate
Apex Memory npm
A
apex-memory

Persistent memory MCP server for AI coding agents

AI, Memory & Reasoning Score 96/100 0 findings 12/wk Cap. Moderate
Vault Master npm
A
vault-master-mcp

MCP server for graph-aware Obsidian vault traversal

AI, Memory & Reasoning Score 96/100 0 findings 12/wk Cap. Moderate
Chipsai PyPI
A
chipsai-mcp

MCP server for ChipsAI — manage chatbots, conversations, documents, and AI models from any MCP client

AI, Memory & Reasoning Score 96/100 0 findings Cap. Moderate
Ckg PyPI
A
ckg-mcp

Context optimization for AI agents — 97 domain knowledge graphs (68 free + 29 Pro), MCP-native traversal. 4× F1 of RAG, 11× fewer tokens per query. Works with Claude, GPT-4o, Gemini, and any MCP client.

AI, Memory & Reasoning Score 96/100 1 finding Cap. Moderate
Ckg Agentforce PyPI
A
ckg-agentforce

Salesforce AgentForce as a traversable knowledge graph — 40 nodes, Einstein Trust Layer, Resolution Criteria, 2-dollar-per-resolution billing path. 11x fewer tokens than RAG. MCP-native.

AI, Memory & Reasoning Score 96/100 0 findings Cap. Moderate
Confluence Rag PyPI
A
confluence-rag-mcp

Standalone Confluence RAG MCP retrieval server backed by SQLite/sqlite-vec.

AI, Memory & Reasoning Score 96/100 0 findings Cap. Moderate
Coordmcp PyPI
A
coordmcp

A FastMCP-based Model Context Protocol server for intelligent multi-agent code coordination

AI, Memory & Reasoning Score 96/100 1 finding Cap. Moderate