AI & Agents MCP Servers for OpenAI Agents SDK

Mailbox + wake system for AI agent teams: letters always land, right agent wakes, quiet otherwise.

MCP proxy server that allows MCP clients to communicate with agent servers (Mastra, LangGraph, etc.)

MCP server for AgentForge — trust audit (check_trust, evaluate_policy, list_trusted, recommend) plus action tools (discover

Tamper-evident, SHA-256 hash-chained audit trail and observability for AI agents.

Durable execution and named concurrency queues for coding agents across local, SSH, and Slurm.

Reference MCP server: a demo bakery agents can query for hours, menu, availability, and orders.

Local MCP broker that exposes one compact entry for many upstream servers.

MCP server fronting a self-hosted coordination-bus HTTP API: post/read/claim/release/heartbeat.

MCP adapter for the DAiL agent-to-agent marketplace: escrow-protected trade via stdio.

Polyphonic meritocratic ensemble for Universal IDEs

MCP gateway: bounded tool shortlists + artifact-backed result firewall. Deterministic, no model.

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

[DEPRECATED] No longer maintained — Gemini CLI stops serving its free/Pro/Ultra tiers on 2026-06-18 (Google is moving to Antigravity CLI)

MCP server for Gemini CLI OAuth integration

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

Block prompt injection, evasive spacing, and obscene content before it reaches your LLM.

Relays messages between two Claude Code sessions on different machines using the Channels API

Comprehensive MCP server for Langfuse - Traces, Scores, Datasets

MCP server for interacting with LLMs using LlamaIndexTS

Grade an MCP server's auth against the spec and diagnose which layer a failure is in.

Model-tiered content pipeline — cheap models seed, expensive models verify