890 reviewed MCP servers in this category · page 7 of 15 · all categories
Knowledge and memory MCP servers give assistants a persistent brain: knowledge graphs that survive between sessions, structured reasoning scratchpads, and connectors into your personal notes. They fix the most annoying thing about LLMs — walking into every conversation with total amnesia.
Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector
Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.
Hot-reload monitor for MCP servers - like nodemon but for Model Context Protocol
AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).
A Model Context Protocol server
Your AI development companion. An MCP server that gives your AI persistent memory, structured specifications, and adaptive change management — so it
👉 **Start here:** <https://hunter.io/api-documentation#mcp>
An MCP server that provides tools for fetching, converting, and extracting data from web pages.
Please refer to the new repository for the latest updates and contributions.
The Ilograph MCP Server is a [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) server that provides AI agents with
<strong>Persistent memory for AI coding tools. 100% local. Zero API cost.</strong>
Private context layer for AI agents: web, docs, code search, dep graph, memory, planning.
A lightweight MCP server for encrypted memory management with Claude
Interactive LeetCode MCP server with authorization and submission capabilities for seamless problem-solving with Claude
MCP server for Cisco Intersight API
Most AI agents still explore documentation the expensive way:
A Model Context Protocol (MCP) server for interacting with [Joe Sandbox Cloud](https://jbxcloud.joesecurity.org/). This server exposes rich analysis
MCP server for Julia documentation and source code access
A Model Context Protocol server for Jupiter
A lightweight JVM monitoring and diagnostic MCP (Multi-Agent Communication Protocol) server implementation based on native JDK tools. Provides AI
Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.
Search the web using Kagi's search API
MCP server for key driver and feature importance analysis based on rule mining
`kg` gives your AI assistant persistent, structured, editable project memory stored locally as a knowledge graph.
CLI-first MCP server for Composer-based Kirby CMS projects. It lets an IDE or agent inspect your Kirby project (blueprints, templates, plugins, docs)
Zerodha Kite MCP server
# Klaviyo API MCP Server A comprehensive Model Context Protocol (MCP) server for interacting with Klaviyo's API. This server provides tools and
Register Knowerage wherever your MCP host expects server definitions (for example some clients use `.cursor/mcp.json` or `.vscode/mcp.json`; others
MCP server for enabling persistent knowledge storage for Claude through a knowledge graph with multiple storage backends
Knowledge graph & long-term memory for AI agents: recall, relations, store, stats, health.
Shared debugging memory for AI coding agents
Code indexing for better AI code generation
This MCP server enables Claude to search file content using ripgrep - with extra features for Obsidian. It understands Obsidian-specific elements
Memory for AI coding agents — markdown in your own git, not a vendor database. Apache-2.0.
MCP tool for distributed graph memory bank storage in KuzuDB for coding agents
Semantic search for LangChain, LangGraph, LangSmith & DeepAgents docs and source code.
This Streamlit application provides a user interface for connecting to MCP (Model Context Protocol) servers and interacting with them using different
Model Context Protocol (MCP) server for accessing and searching Laravel 12 documentation. Enables AI assistants and tools to query Laravel docs
Listed in the [official MCP Registry](https://registry.modelcontextprotocol.io/?search=laravel-mcp-companion) as
A Model Context Protocol (MCP) server for Lerian portfolio discovery, documentation, learning, SDK examples, live product API discovery/execution
Context GC for LLM agents: offload large tool outputs and recall them to save tokens.
MCP server for the Lettr email API — send transactional emails, manage templates, domains, and webhooks from any AI assistant
Episodic memory and architectural policy for AI agents. Frames, Atlas, and Policy.
Patent and invention management for AI assistants: capture, analyze, and submit inventions.
MCP server for Limelink dynamic link management
Connect AI assistants to Limitless for personal memory and lifelog access
Persistent engineering memory for AI coding agents. Survives refactors, knows when it is stale.
Link gives Codex, Claude, Cursor, Kiro, VS Code, Copilot, Antigravity, and other local agents the same source-backed memory, stored locally as
A Model Context Protocol (MCP) server that automates generating professional LinkedIn post drafts from YouTube videos. This tool streamlines content
Local-first agent memory MCP — cross-agent brain with drift detection, 6-layer structured memory + token-saving file diff cache
Linux MCP server for real-time system monitoring - CPU, memory, disk, network, processes, Docker.
a light weight version of mcp sdk inspired by official model context protocol sdk, NOW focus on sse only no stdio
LLDB MCP server
Getting the right context into LLM conversations is friction-heavy:
Search and install 20,000+ security-graded MCP servers and agent skills.
MCP server: inspect, manage, kill local dev servers. Stop guessing what's on :3000.
Ever wanted the ChatGPT memory feature but **across all your LLMs** and stored on **your own hardware**? Ever hate how there's a **limit to how many
Hierarchical markdown memory palace for AI agents — structured palace navigation via MCP tools.
Agents need durable memory, and you already maintain one — your graph. The missing piece is access you can trust: an agent should read broadly and
Local-first personal knowledge base. Cited answers from your vault via vector + graph retrieval.