Tag: mcp-protocol

Type: All Skills Tools
tool ★ 19

Pre-action gates for AI agent safety

ThumbGate implements pre-action gates for AI agents, capturing structured thumbs-up/down feedback to generate prevention rules from repeated failure patterns. It intercepts tool calls via the MCP PreToolUse hook, blocking known-bad actions …

IgorGanapolsky/ThumbGate agent-safety llm-guardrails mcp-protocol coding-agent
tool

Agent Safety Gates and Failure Pattern Prevention

ThumbGate implements pre-action gates for AI agents, capturing structured thumbs-up/down feedback on tool usage. It automatically generates prevention rules from repeated failures, blocking known-bad patterns before execution via the MCP Pr…

IgorGanapolsky/mcp-memory-gateway agent-safety llm-agents prevention-rules feedback-loop
tool ★ 2

Agentic AI memory and reasoning backend

This tool provides a deterministic backend for agentic AI, managing semantic memory, truth maintenance, and multi-step reasoning. It exposes core functionality via MCP, REST endpoints, and dedicated SDKs for fact assertion, querying, and ru…

Auctalis/nocturnusai agentic-ai reasoning memory-management mcp-protocol
skill ★ 136,096

Building Model Context Protocol Servers for LLMs

This guide outlines the process for developing Model Context Protocol (MCP) servers, enabling sophisticated LLM interaction with external APIs. Developers can implement these servers using Python or TypeScript, ensuring robust tool definiti…

anthropics/skills mcp-protocol llm-agent api-server typescript