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.

Tmcp Session Manager Source verified npm
A
@tmcp/session-manager

Session management for TMCP (TypeScript Model Context Protocol) transport implementations. This package provides the base classes and in-memory implementations for both streaming session coordination and session metadata persistence.

AI, Memory & Reasoning Score 100/100 0 findings 2.4M/wk Cap. Minimal
Sequential Thinking (official) Official 3 implementations
A
best: @modelcontextprotocol/server-sequential-thinking

The official structured-reasoning server: break problems into revisable thought sequences.

AI, Memory & Reasoning Best score 100/100 1 finding 103k/wk Cap. Minimal
Memory (official) Official 32 implementations
A
best: @modelcontextprotocol/server-memory

The official knowledge-graph memory server: persistent entities, relations and observations.

AI, Memory & Reasoning Best score 100/100 0 findings 74k/wk Cap. Minimal
Apps Official npm
A
@n8n/mcp-apps

MCP Apps UI resources and server helpers for n8n

AI, Memory & Reasoning Score 100/100 0 findings 39k/wk Cap. Minimal
Agent402 Source verified npm
A
agent402-mcp

Open-source MCP server exposing Agent402.Tools' catalog — 500+ strong: 400+ self-hostable tools + 100 multi-tool skill packs (security-audit, trend-analysis, structured-scrape, decode-blob, forecasting-bake-off) for AI agents — browser, web search & answe

AI, Memory & Reasoning Score 100/100 0 findings 878/wk Cap. Minimal
Ollama Source verified npm
A
ollama-mcp-server

Modern MCP server for Ollama – rebooted and actively maintained.

AI, Memory & Reasoning Score 100/100 0 findings 488/wk Cap. Minimal
Bookstack Source verified 2 implementations
A
best: bookstack-mcp-server

MCP server providing comprehensive access to BookStack knowledge management system

AI, Memory & Reasoning Best score 100/100 0 findings 413/wk Cap. Minimal
Megamemory Source verified npm
A
megamemory

MCP server that gives coding agents persistent project understanding via a knowledge graph

AI, Memory & Reasoning Score 100/100 1 finding 340/wk Cap. Minimal
Markdown Vault Source verified npm
A
@wirux/mcp-markdown-vault

Headless semantic MCP server for Obsidian, Logseq, Dendron and any markdown-based knowledge base

AI, Memory & Reasoning Score 100/100 0 findings 323/wk Cap. Minimal
Neurodivergent Memory Source verified npm
A
neurodivergent-memory

A Model Context Protocol server for knowledge graphs designed around neurodivergent thinking patterns

AI, Memory & Reasoning Score 100/100 0 findings 294/wk Cap. Minimal
Neo4j Knowledge Graph Source verified npm
A
@henrychong-ai/mcp-neo4j-knowledge-graph

Neo4j-based knowledge graph with temporal versioning and semantic search.

AI, Memory & Reasoning Score 100/100 0 findings 288/wk Cap. Minimal
Littlebigbrain Source verified npm
A
@littlebigbrain/mcp

MCP server for little big brain — graph and hybrid search tools for agents

AI, Memory & Reasoning Score 100/100 0 findings 259/wk Cap. Minimal
Xmind Source verified npm
A
@41px/mcp-xmind

MCP server for XMind

AI, Memory & Reasoning Score 100/100 0 findings 240/wk Cap. Minimal
Foundryvtt Source verified npm
A
foundryvtt-mcp

Model Context Protocol server for FoundryVTT integration

AI, Memory & Reasoning Score 100/100 0 findings 239/wk Cap. Minimal
Notes Source verified 2 implementations
A
best: @abhishekmcp/notes

MCP server for local markdown notes — ranked search, tags, todos, and a wiki-link knowledge graph, from any MCP client.

AI, Memory & Reasoning Best score 100/100 0 findings 230/wk Cap. Minimal
Site Source verified npm
A
@bounded-systems/site-mcp

Read-only MCP server over robertdelanghe.dev's signed static API. A thin implementation of @bounded-systems/static-mcp: the site's verbs + resource catalog + config, served as a Sigstore-verified static-response MCP server over stdio.

AI, Memory & Reasoning Score 100/100 0 findings 229/wk Cap. Minimal
Mushi Mushi Source verified npm
A
@mushi-mushi/mcp

MCP server for Mushi Mushi — triage user-felt bugs, pull evidence (screenshots, console logs, network requests), check blast radius, and dispatch fix PRs, all from your AI coding agent

AI, Memory & Reasoning Score 100/100 0 findings 192/wk Cap. Minimal
Memory Keeper Source verified 2 implementations
A
best: mcp-memory-keeper

Persistent context management for AI coding assistants so context survives across sessions.

AI, Memory & Reasoning Best score 100/100 5 findings 181/wk Cap. Minimal
Scrapbox Cosense Source verified npm
A
scrapbox-cosense-mcp

MCP server for cosense

AI, Memory & Reasoning Score 100/100 0 findings 157/wk Cap. Minimal
Serpdive Source verified npm
A
serpdive-mcp

MCP server for SERPdive, the AI Search API: real-time web search returning answer-ready page content for LLMs and agents. Same speed as Tavily, 20.2% fewer tokens, 60.7% of decided quality duels on a public benchmark.

AI, Memory & Reasoning Score 100/100 0 findings 117/wk Cap. Minimal
Agentsmd Memory Source verified npm
A
agentsmd-memory

Zero-dependency MCP server that gives AI agents a self-updating project memory in AGENTS.md. Returns merge instructions instead of mutating state, so every change is a reviewable diff.

AI, Memory & Reasoning Score 100/100 0 findings 105/wk Cap. Minimal
Siyuan Source verified npm
A
siyuan-mcp

Safe, structured Model Context Protocol server for SiYuan Note

AI, Memory & Reasoning Score 100/100 0 findings 105/wk Cap. Minimal
Builderforce Memory Source verified npm
A
@seanhogg/builderforce-memory-mcp

BuilderForce Agent Memory — MCP transport. Exposes @seanhogg/builderforce-memory to any MCP client (Claude Agent SDK in-process, stdio, or HTTP) over a pluggable MemoryBackend, with token-saving fetch-on-demand recall.

AI, Memory & Reasoning Score 100/100 4 findings 94/wk Cap. Minimal
Slimcontext Source verified npm
A
slimcontext-mcp-server

MCP Server for SlimContext - AI chat history compression tools

AI, Memory & Reasoning Score 100/100 0 findings 91/wk Cap. Minimal