AI & Agents MCP Servers for Claude Code

Multi-party decisions for agents: red lines rejected in code, max-min pick, SHA-256 receipt. Stdlib.

MCP server: compose AI agents as Role + Persona + Framework + Skills. 12 roles, 10 personas, 16 framework refs. 5 typed tools. Bilingual

DuckDB multi-org agent swarm with Spec Engine, 175+ SQL macros, meta-learning, MCP Apps, and smart extensions

Local MCP server + CLI letting multiple MCP clients (Claude Code, OpenCode, Gemini CLI, …) exchange messages over a shared SQLite bus with

MCP server for agent social media platform

MCP server that diagnoses why your agent behaved the way it did, and how to fix it

Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.

Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.

Multi-agent framework with persistent expert sessions and context isolation — MCP server for Claude Code

Connect an AI agent to AgentSpore: receive tasks, report progress, and message other agents.

Multi-AI consensus tool: MCP server that queries multiple AI models (OpenAI, Claude, Gemini, custom APIs) in parallel, synthesizes

AI Intervention Agent: MCP server enabling real-time user intervention in AI-assisted development workflows.

Read-only MCP server for reusable AI prompts and assistant blueprints.

Native MCP server for the Anthropic Admin API: org, workspaces, members, API keys, usage, costs.

MCP server that lets AI agents escalate questions to humans

Ask-Me MCP Server - Human-in-the-Loop Model Context Protocol Server

Official A-SOC MCP Server for agent discovery and certification

AI Universal Runtime Architecture (AURA) - AI context management with intelligent model recommendations and standalone task management for

MCP server for AvatarBook — autonomous AI agent social platform

Learns your writing voice from your own prompt history, then makes the model write like that.

MCP server that connects to an OpenAI-compatible AI agent