AI & ML MCP Servers

A content exploration toolkit that helps LLMs surface high signal, unsummarized web content.

A lightweight, structured, token-efficient local-first MCP memory server

MCP server for image/video understanding & generation (Gemini/OpenAI/Grok)

OpenAI-compatible AI inference, code, embeddings & agent tools for bots — and mine ANM.

Debug microcontrollers via OpenOCD: flash, breakpoints, memory, registers and variables.

Compiles structured specs into SCORM 1.2/2004 e-learning packages. 30 tools, quality gate, no LLM.

Domain-specific LLM fine-tuning — sovereign models trained on your data, zero infrastructure.

Cognitive memory for AI coding assistants — persistent memory across sessions

Governance for LLM agents: 7 enforced rules + read-only reference tools. Safe in any MCP client.

Deterministic guardrail your coding agent runs on itself: diff-scoped findings, zero LLM tokens.

MCP server exposing Martin Fowler's refactoring catalog to LLMs with 71+ refactorings

Local audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.

Read-only visualization for Cortex memory, knowledge, sessions, traces, and codebase graphs.

MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.

MCP server for local speech translation (EN ↔ 中文) via Whisper + Claude + Piper

Local Git-history memory for coding agents: reverts, suppressions, hotspots, and annotations.

Assembly-accelerated DuckDB MCP server for code search, indexing, and symbol lookup.

Generate and edit images and video via OpenRouter or any OpenAI-compatible API.

Associative key-graph memory for LLM agents — recall by association, not vector similarity.

30 GPU-powered AI services as MCP tools. LLM, image, video, audio, embeddings & more.

Query and retrieve information about various adversarial tactics and techniques used in cyber atta…

ADIF 3.1.6 parser and validator for amateur radio QSO logs. Full spec coverage.

Stateful memory for AI agents. Temporal awareness, error loop detection, and preventive constraints.

Local-first memory & context-handoff across AI tools — capture in one, resume in another. No cloud.