AI & Agents MCP Servers for OpenAI Agents SDK

Sealgate gateway proxy: list governed MCP servers and review agent session and audit status.

Ethics Filter Framework MCP server

Give your agent a body: observe and control simulated robots (LIBERO, RoboDojo) over MCP.

🛡️ Make AI interrupt itself and challenge your thinking. Turns Claude into a philosophical sparring partner who actively contradicts

160K deductive JSON persona constraints. 0 drift breaks in 120 turns. Free API, no key.

A thin, auditable MCP server wrapping the Gemini CLI. Forward-compatible with future CLI flags via extra_args passthrough.

MCP server enabling AI expert debates - Dynamic expert generation for personalized multi-round philosophical discussions on any topic

Local gut check before risky agent actions: calibrated safe/intended probabilities, no API calls.

Turn-level governance observability for Claude Code transcripts. Local-first, no LLM inside.

Read-only MCP server for the HeyClaude registry.

MCP server for AI Agent interview simulation with RAG knowledge base

40+ pay-per-use tools for AI agents: search, TTS, QR, PDF, scraping, image gen. x402.

Three-model MCP server returning Grok, Gemini, and DeepSeek outputs for Claude.

Local MCP server for AI agents: local YOLO-based UI-element detection (OmniParser-v2 icon detector) with per-element OCR, hash caching, and

MCP server for KoboldAI API integration

Model Context Protocol server for AI-assisted development with Kubeflow

Make AI tasks repeatable. Run with new data automatically — zero AI tokens per run.

Comprehensive MCP server for Langfuse - Traces, Scores, Datasets

Human-in-the-Loop API: AI agents create forms, share URLs with humans, get JSON back.

MCP server bridge for Claude and llama.cpp - Connect Claude Desktop to your local models

MCP server that completes prompts with automatic provider fallback across OpenAI, Anthropic Claude, and Google Gemini. Handles rate limits