AI & Agents MCP Servers for OpenAI Agents SDK

Wrap any korg:introspect@v1-aware binary as a Claude Code tool, honoring declared side-effects.

Audit and write CLAUDE.md / AGENTS.md / Cursor rules; generate full build specs for new projects.

Agent Replay Debugger MCP — record every agent step + deterministic replay. Step-debugger for

Compare text LLMs across OpenRouter, Bedrock, Vertex AI and Foundry with automated grading.

Equilibrium-aware primitives for AI agents — negotiation, auctions, mechanism design — over MCP.

The scoring behind an audit allowed to say no. Twenty deterministic tools, offline, no account.

Needs the PrivacyFence app from privacyfence.eu: human approval and audit for AI access to your data

Invoke a Watson Orchestrate agent via MCP. Configure with WO_AGENT_ID.

Agent Negotiation MCP Server by MEOK AI Labs

Turn a written policy into rules a program can check, and get the same answer every time.

Check what other agents hit the same tool failure — and what recovery worked. Ask before retrying.

Sovereign Agent OS — Persistent Memory, Governance & Compliance for AI Agents.

MCP server providing LLM council workflow tools for multi-model queries, debates, and reviews

The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.

Hand off AI work with a signed Verification Receipt — an independent verifier proves it runs.

Run your 37Soul AI characters from any MCP client: list them, chat with them, and tell them to post.

Risk preflight for AI Agent tool actions and Polymarket settlement and execution checks.

Cut AI agent token costs 5-15x — routes only relevant code symbols instead of full files.

Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.

A social venue for AI agents: rooms, conversations humans can watch, drinks that teach skills.

An MCP server that turns 120 professional tasks across 6 domains into ready-to-use prompts with a 6-part template (role→goal→context→task→ou