"OpenAI Gym" matching MCP servers:

Records and scores prospective equity earnings predictions made by AI agents, allowing comparison of different agent configurations.

Drop-in stdio interceptor that gates MCP tools/call requests through a YAML policy (block / require_approval / audit / budget cap) before they reach the real server. The same policy file is reused by @jamjet/claude-code-hook and @jamjet/openai-guardrail, so one rule set covers Claude Desktop, Cursor, OpenAI Agents, and custom clients.

Gives OpenAI Codex behavioral history from workspace.json, exposing file fragility and co-change partners as tools to enforce safer edits and block incomplete patches.

A tiny MCP server that wraps Perseus Vault to provide persistent, encrypted, local-first memory for OpenAI Codex agents, enabling them to remember project conventions, decisions, and context across sessions.

Universal Git-powered persistent memory, context rules & native MCP server for AI coding agents. Prevents context amnesia with stateful workflows, Git Notes, and cross-model review gates across Claude, OpenAI, Gemini & DeepSeek in Cursor, Claude Code & VS Code.

Enables local OpenAI Codex or Anthropic Claude Code clients to connect to Spicy Studio, guiding client sign-in and browser-based pairing so users can share selected stories or creative briefs and receive reviewable text or structured short-drama drafts.

Enables AI assistants to explore and interact with the Facets Control Plane API via natural language, supporting operations like searching endpoints, loading schemas, and making authenticated API calls.

Enables MCP hosts to render OpenUI artifacts (inline or sidecar) for agent-generated UI components such as cards, dashboards, forms, and charts, with validation, versioning, and security controls.

Let Claude Code, Claude Desktop, OpenAI Codex, Kimi and any MCP-capable AI agent create, launch, check and drive your Nullprint browser profiles. Install with one command: claude mcp add nullprint -- uvx nullprint-mcp

MCP server for Zhipu GLM chat completions via AceDataCloud. Provides tools for chat completions, model listing, and usage guide.

Connects MCP clients such as Claude Desktop, Cursor and Claude Code to an OpenAI- and Anthropic-compatible AI gateway, enabling chat with Claude, GPT, Gemini, Grok and Kimi models, listing available models, and looking up per-million-token pricing. It also sends one prompt to several models in parallel and returns each answer with token usage, latency and estimated cost.

173 tools to automate Google Ad Manager — campaigns, creatives, inventory, reporting via natural language

MCP server for Portuguese Parliament open data, enabling AI agents to access legislative initiatives, deputies, plenary votes, petitions, and parliamentary committees.

Image and video generation through the Modelflare OpenAI-compatible API gateway (MCP server).

An MCP server that bridges multiple LLMs (OpenAI-compatible APIs and CLI coding agents) for collaborative debugging and diverse AI perspectives.

Production-grade MCP server for the Google Tag Manager API v2 with read-only GA4 (Admin + Data API) tooling. 107 tools covering the full GTM surface, including server-side containers. Ships read-only: writes, publishes, and deletes are each gated behind separate opt-in flags, every mutation requires per-call confirmation, and a dry-run mode simulates changes. Includes container audits

A server that provides management and connectivity for Alibaba Cloud RDS database services via OpenAPI, enabling users to create, query, and modify RDS instances through MCP integration.

远程MCP服务，通过Model Context Protocol为AI应用提供阿里云数万个OpenAPI的无缝集成，支持Terraform、多账号、自定义OAuth等能力。

MCP server that routes AI chat requests to the best available provider (Anthropic, OpenAI, Groq, etc.) with automatic fallback, budget caps, and model-tier routing.

Automatically converts any apcore-based project into an MCP server and OpenAI tool provider with zero code changes.

It enables OpenAI models to create and join secure deliberation rooms, post messages, verify Ed25519 W3C DIDs, reach 67% Byzantine-fault-tolerant consensus, manage Atlas 2.0 goal DAGs with rollback, and escalate high-risk actions through fail-closed human approval gates.

Automatically converts OpenAPI specifications into a Model Context Protocol (MCP) server instance.

Enables transparent proxying of upstream MCP servers and OpenAI/Anthropic API calls so large tool responses are handle-ified and can be queried with universal verbs, cutting token usage while preserving access to full payloads.

Orchestrates Claude Code and OpenAI Codex to plan, implement, review, and verify code changes via pull requests with security controls.

A local MCP runtime that lets MCP clients such as ChatGPT inspect workspaces, search, read, write, and patch files, manage directories, run shell commands, and control persistent processes on your machine through an outbound Device Relay connection that needs no open inbound port. It can also publish a local loopback OpenAI-compatible model runtime as a Frely personal Provider.

Enables building AI-powered Slack apps using the Slack MCP server and OpenAI models for automated messaging and canvas creation.

A toolkit that enables AI assistants to directly call Feishu/Lark API interfaces for automation scenarios like document processing, conversation management, and calendar scheduling.

MCP server to mock OpenAI, Anthropic, and Google Gemini responses for testing AI integrations without real API keys or token spend.

Analyze Amazon reviews, VOC feedback, sentiment, pain points, and listing improvements through seven curated MCP tools.

Enables AI assistants to securely access Webull trading and market data, including real-time market data, screener, watchlist, fundamentals, and order placement across multiple regions.