ChatGPT MCP Server
This server provides one ChatGPT tool for asking prompts anonymously and receiving markdown answers with the web sources ChatGPT consulted.
Send prompts up to 8,000 characters to ChatGPT without an OpenAI account or API key.
Receive the answer as markdown, plus the generated conversation title, answering model, completion status, and whether web search was used.
Get structured source data such as title, URL, domain, and sometimes snippet or publication date.
Set an IANA timezone to define what “today,” “this week,” or “latest” means.
Control answer language by writing the prompt in the desired language.
Use it for cited Q&A, grounding agents or RAG pipelines, summarizing current events with sources, or building datasets of model answers.
Note that each request is a fresh conversation with no memory, and answers without web search may have no sources.
Provides a ChatGPT query tool that sends a prompt anonymously and returns ChatGPT's answer as markdown, along with the web sources it consulted, conversation title, model, and whether web search was used, without requiring an OpenAI account or API key.
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 MCP Server Ask ChatGPT what the Artemis program's current status is and cite its sources."
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 Server
A hosted ChatGPT MCP server that gives Claude, Cursor, Windsurf and any other MCP client one ChatGPT tool. Send a prompt anonymously and get the answer back as markdown together with the web pages ChatGPT consulted, as structured JSON, with no OpenAI account and no API key of your own.
1,000 free credits every month, no card required, which is 100 prompts.
https://mcp.hasdata.com/mcp?apis=chatgpt
Contents
Related MCP server: WebChatMCP.js
What you need
An MCP client and a HasData API key from the dashboard, free to create with no card, and the free tier covers 100 calls a month at the 10-credit rate. This is a remote server, so the simplest path is a URL and an x-api-key header, with no container to run and no OpenAI billing anywhere in the flow. A client that only speaks stdio reaches it through a thin launcher, published as @hasdata/chatgpt-mcp on npm and hasdata-chatgpt-mcp on PyPI, shown below.
Quick start
The server URL is the same for every client. We run it hands-on in Claude Code and Claude Desktop. The other blocks follow each client's own documented format for a remote server.
Field | Value |
URL |
|
Transport | HTTP, streamable |
Auth header |
|
Clients with OAuth support can add the same URL as a connector and sign in without putting a key in a config file.
claude mcp add --transport http chatgpt "https://mcp.hasdata.com/mcp?apis=chatgpt" \
--header "x-api-key: HASDATA_API_KEY"{
"mcpServers": {
"chatgpt": {
"type": "http",
"url": "https://mcp.hasdata.com/mcp?apis=chatgpt",
"headers": { "x-api-key": "HASDATA_API_KEY" }
}
}
}{
"mcpServers": {
"chatgpt": {
"type": "streamable-http",
"url": "https://mcp.hasdata.com/mcp?apis=chatgpt",
"headers": { "x-api-key": "HASDATA_API_KEY" }
}
}
}{
"servers": {
"chatgpt": {
"type": "http",
"url": "https://mcp.hasdata.com/mcp?apis=chatgpt",
"headers": { "x-api-key": "HASDATA_API_KEY" }
}
}
}Example prompts
Prompts, not code. Paste one in and the agent picks the tool itself. Each is annotated with the calls it takes, because every successful call costs 10 credits.
Ask ChatGPT what the current state of the Artemis program is, and list the sources it used.
One call, 10 credits. The answer and the sources come back together.
Ask ChatGPT the same question in German.
One call, 10 credits. The answer follows the language of the prompt, so write the prompt in the language you want back.
Ask ChatGPT what happened in AI this week, with Berlin as the current date.
One call, 10 credits. timezone is what fixes the meaning of "this week".
Put the same question to ChatGPT three times and show where the answers differ.
Three calls, 30 credits. Each request is a fresh conversation, so there is no carry-over between them.
Tools
Tool | What it returns |
| The answer as markdown, the web sources ChatGPT consulted with their domain and title, the conversation title it generated, the model that answered, and whether a web search was used. 10 credits a call |
One tool, 10 credits per successful call.
Ask ChatGPT
hasdata_chatgpt_chat_getChatgptAnswer
Parameter | Type | Required | Notes |
| string | yes | The question or instruction, up to 8000 characters |
| string | IANA zone name such as |
Everything lands under conversation. The answer is in answer as markdown, with title holding the name ChatGPT generated for the thread, model the model that answered, and usedWebSearch saying whether it went to the web at all. finishReason and complete tell a truncated answer from a finished one.
{
"conversation": {
"answer": "As of **October 5, 2026**, NASA's Artemis program has made substantial progress…",
"title": "Artemis developments cited",
"model": "gpt-5-6",
"usedWebSearch": true,
"finishReason": "stop",
"complete": true,
"sources": [
{ "title": "Artemis News - NASA", "url": "https://www.nasa.gov/artemis-news/", "domain": "www.nasa.gov" }
]
}
}Errors and failure paths
Your client almost never sees an HTTP error code from a tool call. The MCP layer answers 200 and puts the failure inside the result, with isError set to true and the reason as text.
sources is uneven, and partly absent. In a measured answer carrying twenty sources, every one had title, url and domain, eleven had publishedDate and only five had snippet. Read each field defensively rather than assuming the shape of the first element holds for the rest.
No web search means no sources. usedWebSearch is false when ChatGPT answers from the model alone, and sources is then empty or missing. A prompt about a stable fact often takes that path, so ask for current information when citations are the point.
Every call is a fresh conversation. There is no memory between requests, so a follow-up has to carry its own context in the prompt. conversationId identifies the thread that answered, not a thread you can continue.
A truncated answer still succeeds. Check complete and finishReason before treating answer as the whole response.
Each successful call spends credits from the connected account. A call that fails validation is not billed.
Pricing, free tier and limits
The ChatGPT tool costs 10 credits per successful call. Answer length does not change the price.
The free tier is 1,000 credits every month with no card, which is 100 prompts.
Paid plans start at $59 a month for 200,000 credits, which is 20,000 calls. The unit price falls on larger plans. Current numbers are on the plans page.
How it compares
OpenAI API | This server | |
Account | Your own OpenAI account and billing | One HasData key |
What you get | The model's answer | The answer plus the web sources behind it |
Web search | A separate tool you wire up | Included, with |
Output | Your own schema | Parsed JSON with the sources already split out |
The two are not substitutes. The OpenAI API is the right call when you need system prompts, tools, streaming and conversation state. This server is the right call when you want what ChatGPT publicly answers, with its citations, and no account of your own.
FAQ
Do I need an OpenAI account or an API key?
No. The server answers anonymously through HasData, and the only credential involved is your HasData key.
Which model answers?
Whichever ChatGPT serves anonymously at the time. The response reports it in model, so read it rather than assuming. A measured call returned gpt-5-6.
Can I continue a conversation?
No. Each request is a fresh thread with no memory of earlier ones. Carry the context in the prompt instead.
What language will the answer be in?
The language of the prompt. Ask in German and the answer comes back in German, or ask explicitly for a language in the prompt.
Is HasData affiliated with OpenAI?
No. HasData is an independent web data provider and is not affiliated with, endorsed by or sponsored by OpenAI. All trademarks belong to their owners.
Compliance and personal data
The server reads what ChatGPT answers publicly to an anonymous visitor. It does not log in, and it does not reach private conversations or account data.
HasData links
Product page and request builder | |
Endpoint documentation | |
Server documentation | |
Every tool in one server | |
Client walkthroughs | |
Plans and credit costs |
Development
npm install
npm testThe tests in test/ assert the tool contract, the part that can break without a commit here. They check that ?apis=chatgpt returns the one expected tool, that its name and required parameter have not changed, that it carries a description, and that a real call still puts the answer under conversation.
Contributing
The parameter table and the sample above were read from the live schema and from real calls rather than from documentation. A correction is welcome when a field or a failure mode has changed. Open an issue with the response you saw.
License
MIT
Available Tools
1 toolhasdata_chatgpt_chat_getChatgptAnswerchatgpt_chat: GET /ARead-onlyInspect
Get ChatGPT Answer
Sends a prompt to ChatGPT anonymously and returns the answer as markdown text, plus every web source ChatGPT consulted with its domain, page title, snippet, publication date and thumbnail, the links rendered inside the answer, the conversation title ChatGPT generated, the model that answered, and whether a web search was used. The language of the answer follows the prompt — write the prompt in the language you want back, or ask for one in it. Set the frame of reference for words like "today" with timezone. Each request is a fresh conversation with no memory of earlier ones. Use to answer questions with cited sources, to ground an agent or RAG pipeline in ChatGPT's web-search results, to summarise current events with their sources, or to build datasets of model answers.
Inputs: prompt (required), timezone.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of confusing it with another. Its purpose (send a prompt to ChatGPT and return the answer plus sources) is unambiguous.
With a single tool there is no mixed convention to penalize. However, the name is an unwieldy prefixed, camelCase string (hasdata_chatgpt_chat_getChatgptAnswer) rather than a clean verb_noun pattern.
The narrow, single-endpoint domain means one tool covers the core capability without redundancy. Still, a one-tool surface is thin and leaves no room for related operations like continuing a conversation or fetching sources separately.
The tool covers a one-shot query with rich metadata, which fits the described use. But it explicitly has no memory, and there is no way to continue or manage a conversation, so multi-turn workflows are a notable gap.
Maintenance
Related MCP Connectors
ChatGPT answers with web search as JSON: citations, sources, brands and products. Bulk prompts.
Live AI-native web search with citations. One tool for every MCP client. Flat per-request pricing.
Read reusable technical experience from other AI agents. Search a real problem with search_memories, then inspect_memory for provenance, evidence, reported outcomes and limitations. Seven anonymous read-only tools also support public agent discovery and Trust Passport inspection/verification. No account or credentials; no publishing, feedback or Candy actions on this endpoint. Operational telemetry may be recorded, but /mcp/chatgpt does not store search query text. Confidence and cryptographic integrity are not proof of truth, safety or independent validation. Writing requires the separate Remnant Agent OAuth connection at https://remnant.dedale-bi.com/mcp/agent-connect. Documentation: https://remnant.dedale-bi.com/connect. Apache-2.0 integration code and examples: https://github.com/Dedale-Project/remnant-connect. The hosted service, backend and knowledge are governed separately.
AI Visibility Isn’t Luck. It’s Signal Alignment. Read-only MCP access to Market Brew, a patented search engineering platform for SEO and AI visibility. Market Brew uses particle swarm optimization and template models to reverse engineer observed search behavior. Inspect ranking models, content alignment, knowledge bases, crawl data, and AI visibility history through a hosted Streamable HTTP MCP server. Requires an enabled Market Brew account and OAuth. Setup guide: https://brew.marketbrew.ai/customer-manual.htm#api-and-chatgpt-read-access
Related MCP Servers
- AlicenseAqualityCmaintenanceProvides access to OpenAI's ChatGPT API with web search capabilities for Claude and other MCP clients. Supports various GPT models with configurable parameters like reasoning effort, temperature, and streaming mode.144 npm3MIT
- AlicenseAqualityBmaintenanceEnables MCP clients to drive ChatGPT's web interface through a built-in persistent browser, requiring only a single manual login. Prompts are sent through temporary incognito chats and the captured answer text is returned as tool results, along with live model listing, login/status probing, and optional HTTP transport.83Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to check ChatGPT connection status, list live models, and run prompts using a ChatGPT Plus/Pro plan via OpenAI's official OAuth and Responses API.1Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables 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.1MIT