"OpenAI Gym" matching MCP servers:

Use OpenAI text, image, speech, transcription, embeddings and moderation models from Claude, Cursor and any other MCP client.

Typed MCP server for OpenAI Ads and ChatGPT Ads via the Advertiser API. Supports account, campaign, ad group, ad, creative, audience, insight, and conversion tools with readonly mode and guarded writes.

Query OpenAI models directly from Claude using MCP protocol.

Provides image recognition capabilities using Anthropic Claude Vision and OpenAI GPT-4 Vision APIs, supporting multiple image formats and offering optional text extraction via Tesseract OCR.

Enables monitoring of job postings by keyword, returning companies currently advertising those roles enriched with firmographics and LinkedIn URLs via Apify.

Detects hiring intent signals by scanning job boards for specific companies. Returns structured role data for outbound sales targeting.

Self-hosted digests of your Telegram channels over MCP: AI summaries, the last digest and raw per-channel messages. Works with OpenAI, Anthropic or local Ollama.

Read-only MCP server for GenieLocker that exposes tools for service status, commercial inventory, live quotes, recipe search, and credit pricing, without enabling purchases or model inference.

Proxy for OpenAI-compatible backends that compacts conversation history before the context window fills, with read-only MCP tools to search and read back the archived originals.

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.

MCP server for exploring and integrating Toss Securities Open API, providing tools to browse endpoints, schemas, and generate code samples.

Turns an existing Express, Hono, Fastify, or Next.js API into a Streamable HTTP MCP endpoint, exposing one tool per OpenAPI operation that runs in-process through the app's existing routes, auth, validation, and handlers. It also serves discovery documents and readiness guidance so models can better understand and call the API.

MCP server for Hubris, an OpenAI-compatible LLM gateway billed in rubles. Exposes the catalogue of 500+ models with ruble pricing, the account balance, and chat completions with full parity to POST /v1/chat/completions.

Secure credential management for AI agents — encrypted storage, auto-refresh, and rate limiting via a single MCP call. Supports OpenAI, Anthropic, Stripe, GitHub, Brave Search, Kalshi, Coinbase, plus generic API key and OAuth2 for any service.

media-gen renders Claude-authored content — SVG markup, HTML documents, or a JavaScript canvas draw() function — into PNG/JPEG/WebP images and MP4 video using headless Chromium and ffmpeg, with no API keys required. It also offers an optional bring-your-own-key path for photorealistic text-to-image and text-to-video generation via OpenAI, Gemini, or fal.ai.

The LinkedIn API and MCP server for AI agents: search, connect, message and enrich on accounts you own, with limits enforced on our server. 20,000+ LinkedIn accounts run on this stack, and under 1% of them have ever been restricted.

Exposes 120+ Chinese frontier AI models (DeepSeek, Qwen, GLM, Kimi, Seedance, MiniMax, Hunyuan, CogVideoX) as MCP tools via one OpenAI-compatible endpoint: chat, image generation, free-model list, and a live first-party price leaderboard. Zero platform fee.

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.

CodebaseAgent-MCP is an MCP server that uses a lightweight RAG pipeline to delegate repository analysis to a dedicated OpenAI-compatible LLM, reducing token consumption by having the primary assistant receive only the relevant findings instead of repeatedly scanning the entire codebase.

async/await for LLM agents: spawn and await sub-agents scheduled on your own GPUs or any OpenAI-compatible endpoint. Every tool call is a scheduled await: a resumed run goes ahead of batch work and back to the replica holding its prefix cache. Durable runs, run trees with budgets, caller fairness, a status page, OpenTelemetry.

Carbon-aware MCP scheduler that defers "do it later" / "by tomorrow" / "overnight" LLM tasks to the cleanest electricity-grid hour inside a deadline — 40-70% lower CO2 per task, 50% cheaper via Anthropic/OpenAI Batch APIs. 9 MCP tools, per-task carbon receipts to local SQLite, Apache-2.0.

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

Enables MCP clients to send prompts anonymously to ChatGPT and receive the markdown answer plus the web sources it consulted as structured JSON. Requires only a HasData API key, with no OpenAI account, API key, or billing needed.

Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to. Covers OpenAI, Anthropic, Azure, Bedrock, Google, and Cohere from each provider's own deprecation pages.

Generates and edits images using OpenAI GPT Image or Google Gemini models, saving every result to disk and returning local file paths so AI assistants can continue working with the images. It enables prompt-based image creation, editing, inpainting, multi-image composition, and model listing through MCP tools.

MCP Bridge is a local-first Linux/Windows desktop app connecting ChatGPT to approved files and Chrome through authorized OpenAI tunnels, with optional shell tools. The Glama-hosted v0.1.0 release is a restricted READ-ONLY documentation demo: five tools can access only bundled public examples, not your computer, browser, credentials, shell, or files.

Universal bi-directional rules and prompt transpiler between Cursor (.cursorrules / .mdc), Claude Code (CLAUDE.md), and OpenAI with 98.5% certified AST parity and in-RAM secret redaction.

MCP server that gives text-only AI agents the ability to understand images via vision tools, including multi-image analysis, OCR, comparison, and structured extraction. It uses providers like OpenAI, Anthropic, Gemini, and OpenRouter to return plain text descriptions.

Detects a company's technology stack from its public web presence. Returns structured tech signals for sales targeting and competitive analysis.

Any MCP server. Anywhere. An OAuth-protected MCP gateway that can also run the servers, plus your Grok subscription as an OpenAI-compatible API.