MCP servers for OpenAI Agents SDK

Action-level governance for AI agents -- control what they DO, not what they SAY

The Supportive Office for your IDE's AI. Empowers Google Antigravity, Cursor, Copilot & Claude with 54 specialized agents, 69+ skills

MCP server for Agent Pocket — remote human approval bridge for AI agents

Git-like undo, revert, and rollback checkpoints for OpenAI Codex CLI. MCP server + hooks snapshot every edit. Restore in one cmd. Free, MIT

The Universal Hub and Multiplexer for AI Agent MCP Servers and Skills

Local research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.

Local-first shared memory sidecar for MCP-capable AI agents.

MCP Server for AgileConfig - exposes AgileConfig configuration center's RESTful API as MCP tools, allowing AI assistants to directly manage

A measurable taxonomy of the AI-generated design look: 27 tells, a Tell Score detector, a CLI, and an MCP server.

AIDA 2.0 - AI asset truth-source management for rules, skills, memories, and summaries

MCP server that provides unified access to organizational knowledge across multiple platforms (local docs, Guru, Notion)

Read-only Objective-to-Capability Trust Router for source-traced MCP/API candidates.

MCP Server for Aibolit

Local-first, source-backed continuity for AI agents via stdio MCP.

Automated AI research toolkit: hypothesis generation, experiments, and paper writing

AlgoThesis MCP server — research stocks, get real short-interest data, and map any topic (people, events, macro) to tickers. Backtest-free

Privacy-first MCP server for allio Tools — 106 utilities that run entirely on your machine. Calculators, converters, developer tools, text

Measures the cost, tokens and duration of a completed agent workflow from its session log.

Persistent semantic memory for SQL databases. Postgres, MySQL, MSSQL, SQLite.

MCP server that exposes Amper's 80+ DeFi tools to any MCP client (Hermes, Claude Code, Cursor, etc.)

Lineage-gated agent memory tools on Postgres + pgvector, enforced by row-level security.