Enables ChatGPT to ask users for decisions or clarification through native question cards with options and free-text input, then continue the task after the user responds.
A Model Context Protocol server that provides real-time Caltrain schedule information, allowing AI assistants to look up train departures between any stations and access station information using GTFS data.
Enables terminal AI coding assistants to interact with web AI chat services through browser automation, supporting multiple platforms like Doubao and ChatGPT.
This MCP server lets a planning/reviewing model (ChatGPT or Codex) start, monitor, retrieve results from, and cancel coding tasks that DeepSeek Harness executes on a local Windows machine. It operates read-only by default within whitelisted project directories, requiring a locally issued authorization before any write-permitted task can proceed.
Enables Codex to use an authenticated ChatGPT Web session as a reasoning and coding backend through isolated browser sessions, without granting ChatGPT direct workspace access.
An MCP server that orchestrates structured multi-round debates between ChatGPT Web and Gemini Web in the same Chrome browser via CDP, requiring no API keys.
Enables ChatGPT web to use local tools like file reading, command execution, and patch application through an MCP server over OpenAI Secure MCP Tunnel.
Enables AI prompting with optional web search, image attachments, and continued multi-turn conversations by driving the Codex CLI bundled in the desktop app under the user's existing plan, with no API key needed. Runs in the background inside a read-only sandbox, so it never touches local files or other apps.
Provides AI assistants with real-time access to the AGNO framework documentation by enabling them to browse, search, and fetch documentation pages. This server allows users to query information about AGNO's Agents, Teams, and Workflows directly through MCP-compatible clients.
Lets coding agents send questions, progress reports and approved PDFs into the user's own signed-in ChatGPT session through a local Chrome extension, then return the reply and its conversation URL. Keeps one ongoing conversation across devices and blocks duplicate or blind re-sends, all without an OpenAI API key.
Enables AI agents to drive a logged-in ChatGPT web session over CDP, including managing projects and chats, sending messages with file attachments, and retrieving long Pro replies.
Enables MCP clients to securely operate on browser tabs shared through OpenClaw's Chrome extension, with ACL checks enforced on every action and no raw CDP passthrough.
Enables MCP clients like Codex to operate chatgpt.com through a dedicated persistent browser profile, allowing chat creation, project management, prompt submission, file uploads, and response reading without using the ChatGPT API.
An unofficial MCP server that lets MCP clients like Codex operate the ChatGPT web interface through a persistent browser, enabling prompt writing, file uploads, message sending, and reading complete responses without using the ChatGPT API.
The AgentOps MCP server provides access to observability and tracing data for debugging complex AI agent runs. This adds crucial context about where the AI agent succeeds or fails.
A local MCP server that provides a safe plan-and-execute workflow for AI coding assistants, storing plans and tasks, and executing agent commands with an allow-list for security.
A generic local MCP plugin base for ChatGPT that ships example status and echo tools, a guided setup wizard for tunnel configuration with DPAPI-protected API keys, and separated persistent versus generated runtime storage. It also provides a bounded metadata-only conditional-read cache that suppresses unchanged read-only responses to save context.
Enables routing context and execution across AI tools like Claude, Cursor, Windsurf, and ChatGPT with a shared memory, task board, and context bus, plus local file conversion.
A thin MCP proxy that connects LLM clients like Claude and ChatGPT to Viraly's platform API, enabling AI agents to perform actions via natural language.
MCP server that enables AI tools to control local browser sessions for ChatGPT, Claude, and other AI services, supporting querying, navigation, file uploads, and artifact management.
Open source AI agent platform with MCP server, browser automation, knowledge packs, and workflow engine. Works with Claude Code, ChatGPT, Cursor, and any MCP client.
Connects selected Chrome tabs to ChatGPT through a private MCP connection so users can inspect pages, snapshot interactive elements, click, fill, select, scroll, navigate, and capture screenshots. Access stays limited to tabs the user explicitly enables, and each tab remains restricted to its current origin.
Provides a standardized interface to interact with LangGraph agents through ChatGPT Enterprise, enabling conversational AI workflows with tools for agent invocation, streaming responses, and thread management.
Enables ChatGPT to control multiple registered Windows devices through a self-hosted gateway, routing Desktop Commander tool calls to specific workers by device ID.
Enables MCP-compatible AI agents and IDEs to send prompts to an active ChatGPT web session and retrieve the completed response without needing an API key.
Enables ChatGPT (or any MCP client) to delegate coding tasks to a local Hermes-backed agent with async job management, supporting read-only investigation, implementation, and continuation of sessions via secure MCP tunnel.
MCP server enabling bidirectional messaging and collaborative development between DeepSeek Harness (DSH) sessions and ChatGPT desktop/Codex CLI sessions, with session ownership management and queued delivery.
Enables ChatGPT to securely control a local workstation via an MCP tunnel, exposing 44 tools for file/project editing, git, process supervision, browser automation, and Office document handling across macOS, Linux, and Windows.
Enables other agents to list, read, start, and steer Codex chats in the macOS ChatGPT desktop app, including sending follow-ups, choosing model/reasoning/speed, interrupting work, and answering approvals. It can run locally or behind bearer-token-protected tunnels for remote monitoring and control.
Exposes local stdio MCP servers to chat AIs through temporary public URLs, providing both a Streamable HTTP gateway and a REST+OpenAPI bridge for integration with ChatGPT and other clients.
Enables web ChatGPT sessions to submit discussion results back to the original Codex task via MCP, allowing the task to continue after the web interaction completes.
Enables ChatGPT to invoke native OpenClaw browser operations directly through an MCP connection, forwarding actions to the local Gateway while preserving runtime errors and providing a local call monitor.
Enables coding agents like Codex to use the ChatGPT web app as a planning and review brain, letting ChatGPT read only needed code via OAuth MCP and submit locally authorized tasks without API keys or repository uploads.
Enables web-based AI clients like Claude, ChatGPT, and Grok to securely operate a local machine through OAuth-gated MCP tools covering files, shell, Git, databases, browser automation, and background tasks.
A transparent message ferry between Claude Desktop and Claude Code CLI, enabling task delegation with any MCP configuration without the bridge needing to know about specific MCPs.
Enables ChatGPT to supervise and control local Codex runtime sessions through a secure MCP interface, managing threads, turns, approvals, events, and recovery without exposing direct file, shell, Git, SSH, or model loop access.
Enables a single MCP connector to route requests to independent local Chat and Codex runtimes, supporting workspace operations, process control, reviews, browser-backed tasks, and Codex workflows through one public ingress.
Enables ChatGPT Plus and Codex agents to use DataRelay Link through a published Agent Plugins package, relaying tool calls to the upstream DRLink Server MCP for authorization and execution.
Enables ChatGPT to manage a self-hosted gateway through browser-based authenticated setup and authenticated tool calls, with encrypted credential storage, server-side administrator key handling, and redaction.
A Chrome side panel hosting multiple AIs (ChatGPT, Claude, Gemini, Grok, DeepSeek) that also functions as an MCP server for downstream agents, enabling multi-model comparison and agent coordination.
Enables ChatGPT or any MCP client to read output from and send instructions to a running Codex CLI session, allowing remote supervision from desktop or phone without restarting the session.
Enables automatic routing of coding tasks between Codex CLI and web ChatGPT using Jev-based decisions plus deterministic rules, so ChatGPT handles planning, debugging, and review when beneficial while Codex executes or finishes small changes. It adds review/debug protocol extensions while preserving the original read-only MCP bridge.
Enables a ChatGPT dot and Claude Code session to exchange requests and replies through a shared HTTPS mailbox, with claim-and-reply handling via a Monitor hook or native channel.
One connector for the whole MCP catalog — 15,000+ servers plus your team's private MCPs — callable from Claude, ChatGPT, Cursor and VS Code through a single OAuth endpoint. No per-server install.
A personal MCP bridge that lets ChatGPT drive a local Codex CLI, translating instructions into Codex app-server threads and returning compact summaries of what Codex did.