ChatGPT Web MCP
Related Servers
Alternatives to ChatGPT Web MCP
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceEnables browser automation over MCP using a real Chrome browser with existing profile, supporting real tabs, downloads, cookies, and RPA workflows.72 npmMIT
- AlicenseAqualityAmaintenanceConnects MCP clients to real browser sessions via a Chromium plugin, enabling LLMs to read, scan, automate, and navigate web pages using the user's existing browser state.10132 PyPI299MIT
- AlicenseNot gradedqualityDmaintenanceEnables browser automation through MCP clients like Claude or Cursor, using the client's existing LLM without requiring an additional API key.Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to control isolated Chromium browser identities, allowing per-account navigation, interaction, and inspection through MCP without requiring Node or CLI installation.2MIT
- AlicenseNot gradedqualityAmaintenanceProvides MCP tools to control real, logged-in Chrome or Brave browser profiles—tabs, navigation, clicks, and typing—with secure profile isolation and no network listener.MIT
- FlicenseNot gradedqualityDmaintenanceEnables browser automation through the MCP protocol, allowing AI agents to control a real browser using accessibility snapshots and natural language commands.-
TDQS
Scored across 33 tools
Most tools are clearly paired as list/select or action/status, but there is meaningful overlap among status-oriented tools like chatgpt_status, chatgpt_capabilities, and chatgpt_browser_lifecycle, and among sending paths like chatgpt_submit_prompt, chatgpt_send_message, and chatgpt_route_new_chat. The descriptions help clarify intended usage, but agents could still easily select the wrong variant in those cases.
The consistent chatgpt_ prefix and the dominant list_/select_/create_/get_ verb pattern make the set predictable. A few name-style deviations such as chatgpt_status, chatgpt_capabilities, chatgpt_answer_tier_status, and chatgpt_project_instructions are noun-like rather than verb-led, but they are minor and still readable.
With 33 tools, the server exceeds the 25+ threshold and feels over-scoped. The count is inflated by multiple overlapping status checkers and several high-level combined variants that duplicate lower-level send/new-chat flows, making the surface heavier than necessary for its apparent purpose.
The core ChatGPT workflows are well covered: sending messages, reading responses, managing history, selecting modes/models/thinking levels, and working with projects. Notable gaps are the lack of delete/rename operations for conversations and projects, and no way to retrieve a full conversation transcript beyond the latest response, but these are workable gaps rather than fatal dead ends.