Skip to main content
Glama

ChatGPT Remote MCP Server

chatgpt_chat: GET /

hasdata_chatgpt_chat_getChatgptAnswer
Read-only

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 where the user is with lat and lon (a point in a city of the target country) — ChatGPT localizes the answer and its web sources to it, and the applied point is returned in conversation.location; without them the answer is localized by the connection's IP, usually the United States. 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.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "hasdata_chatgpt_chat_getChatgptAnswer"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoGPS latitude of the user's location. Requires `lon`.
lonNoGPS longitude of the user's location. Requires `lat`.
promptYesThe question or instruction to send to ChatGPT, up to 8000 characters. A prompt that asks about recent events makes ChatGPT search the web and return sources; a general-knowledge prompt is answered from the model alone. The prompt also decides the language of the answer — write it in the language you want back, or ask for one explicitly ("Antworte auf Deutsch").

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / lat
      Added value: +{
      +  "description": "GPS latitude of the user's location. Requires `lon`.",
      +  "type": "number"
      +}
    • addedInput schema / properties / lon
      Added value: +{
      +  "description": "GPS longitude of the user's location. Requires `lat`.",
      +  "type": "number"
      +}
    • removedInput schema / properties / timezone
      Removed value: -{
      -  "description": "IANA time zone name, for example `America/Chicago` or `Europe/Berlin`. It sets what ChatGPT treats as the current date and time, which matters for prompts that say \"today\", \"this week\" or \"latest\".",
      -  "type": "string"
      -}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the supplied annotations, it discloses the key non-obvious behaviors: each request is a fresh conversation with no memory, localization comes from lat/lon or falls back to the connection IP (usually US), and the applied point is returned in conversation.location. It also explains the language-follows-prompt rule, which is real behavior an agent would otherwise get wrong.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and every clause carries information, but the second sentence is one long run-on enumerating every returned field, which is harder to scan than a short list. The use-case sentence at the end is well-placed; trimming the return-field enumeration into discrete items would improve it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must carry return-value information — and it does, naming each returned artifact including the conversation.location echo. Combined with statelessness, localization defaults, and prompt-language behavior, an agent has everything needed to call this correctly on the first try.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning: it clarifies that lat/lon should be a point in a city of the target country, that they jointly localize the answer and its web sources, and that omitting them defaults to IP-based localization. Only the prompt parameter is merely restated rather than extended.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete verb and resource ('Sends a prompt to ChatGPT ... returns the answer as markdown text') and then enumerates the exact payload: web sources with domain, title, snippet, date and thumbnail, links in the answer, conversation title, model, and web-search flag. There is no ambiguity about what the tool does, and no sibling tools exist that would need differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives four explicit use cases — answering with cited sources, grounding an agent/RAG pipeline, summarizing current events with sources, and building datasets of model answers — plus a prompt-level rule that recent-events prompts trigger web search while general-knowledge prompts do not. What's missing is any when-not guidance or exclusion, so it stops short of a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.