AI & ML MCP Servers

Dynamic and reflective problem-solving through structured thought sequences for complex reasoning tasks.

Knowledge graph-based persistent memory system so AI assistants can remember entities and relations across conversations.

Codebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.

Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.

Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.

Local-first knowledge management with bi-directional LLM sync via Markdown files.

Generate academic diagrams and statistical plots from text using multi-agent AI.

Let any LLM actually watch a video: scene-aware keyframes plus a timestamped transcript, local.

Let any LLM actually watch a video: scene-aware keyframes plus a timestamped transcript, local.

Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.

Local-first personal memory and model server for trusted MCP agents on macOS.

Local-first personal memory and model server for trusted MCP agents on macOS.

Structural codebase MCP server with persistent memory: navigate by symbol, recall across sessions.

Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.

Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.

Local-first persistent project memory for AI coding agents across MCP clients and sessions.

Local-first memory for AI agents that reaches backward to find a failure's root cause.

Local searchable memory over your coding-agent session histories, served back via MCP recall.

Long-term and multimodal memory for AI agents - character-aware, mem0-compatible, fully-local option

AI-powered code indexer with semantic search and knowledge graphs

Open-source LLM knowledge base: team chat into a typed knowledge graph and auto-generated wiki.

Local-first memory + judgment layer for AI coding agents — warns before repeating failed fixes.

Organize Claude Code memories, skills, MCP servers, commands, agents, rules via drag-and-drop.

Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.