chatgpt-mcp
Provides tools to fetch and parse publicly shared ChatGPT conversation links, returning full transcripts as markdown or structured JSON with title, messages, and model information.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@chatgpt-mcpconvert https://chatgpt.com/share/abc123 into a markdown transcript"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
chatgpt-mcp
MCP server for reading shared ChatGPT conversations into Goose.
Paste a ChatGPT share link, get the full conversation transcript. Built for the workflow: ideate in ChatGPT, synthesize in Goose.
Install
cd ~/development/chatgpt-mcp
uv pip install -e .Related MCP server: Webustler
Goose Config
Add to ~/.config/goose/config.yaml:
chatgpt:
enabled: true
type: stdio
name: ChatGPT Reader
description: Read shared ChatGPT conversations
cmd: uv
args:
- run
- --directory
- /Users/dakotafabro/development/chatgpt-mcp
- chatgpt-mcp
envs: {}
env_keys: []
timeout: 30
bundled: false
available_tools: []Tools
fetch_chatgpt_conversation(url)
Returns the conversation as a markdown transcript with role labels.
fetch_chatgpt_conversation_json(url)
Returns structured JSON with title, messages array, model info.
How It Works
Takes a ChatGPT share URL (
https://chatgpt.com/share/...)Fetches the HTML page (no auth needed for shared links)
Extracts conversation data from the React Router streaming payload or
__NEXT_DATA__Parses the message tree (handles branching conversations by walking the mapping)
Returns formatted transcript
Limitations
Only works with publicly shared conversations (via ChatGPT's Share button)
Private/unshared conversations require auth and are not supported
If OpenAI changes their share page HTML structure, the parser may need updating
This server cannot be deployed
Maintenance
Related MCP Connectors
Converts any URL to clean, LLM-ready Markdown using real Chrome browsers
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
Link-preview metadata and clean page-to-Markdown for any public URL. No install.
Clean Markdown and AI-readability scoring for any URL. Built for AI agents.
Related MCP Servers
- AlicenseAqualityDmaintenanceConverts URLs and raw HTML to clean Markdown, enabling AI assistants to read web pages for summarization, analysis, or ingestion.2101MIT
- AlicenseNot gradedqualityCmaintenanceEnables clean, LLM-ready markdown extraction from any URL with automatic anti-bot bypass.3MIT
- AlicenseNot gradedqualityDmaintenanceFetches web pages and converts them to markdown for LLM consumption, supporting chunked reading and raw content extraction.MIT
- AlicenseNot gradedqualityDmaintenanceConverts any webpage into clean, LLM-ready Markdown, removing noise and supporting JavaScript rendering.MIT