AI & Agents MCP Servers for OpenAI Agents SDK

MCP relay server for Claude Desktop <-> Claude Code communication

Give your agent eyes. Search video, images, and audio via the Mixpeek multimodal retrieval API.

MCP server that provides different tools for MLE

Outside-in validation gate for AI-generated text; a separate model checks LLM output, fail-closed.

The agent switchboard: identity, policy, loop-guard, and an append-only audit ledger.

Dispatch a human verifier to physically verify anything in the real world. For AI agents.

Read-only tools over the Psychopathia Machinalis nosology: 79 conditions, 11 tools.

Publish structured, AI-readable business identity data as an MCP server in minutes.

Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.

Query multiple AI models (OpenAI, Anthropic, Google) for consensus responses.

Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.

Human approval for AI agents: a named person approves or rejects, silence is not consent.

Tool selection, Cohere-compatible reranking, and on-chain pricing-truth for agents

MCP server for the Schelling Protocol — AI agent coordination layer

MCP vision server with selectable Google, Anthropic, and opencode backends.

Snap decisions for coding agents: local or hosted classify/check/score/rank via MCP.

Let Codex orchestrate external coding agents through their native harnesses.

Conversation drift visualization for Claude. Color-coded inflection points and one-click forking.

Pay-per-call AI agent utilities via x402 on Base (USDC). 7 tools, $0.003/call.

MCP server for bounded multi-agent committee meetings — Codex + Claude Code deliberate in rounds and self-extinguish on

MCP server for Switchback — classify AI agent turns by complexity and pick the cheapest model that can handle them. Drop-in for Claude