Namequota in ChatGPT

Questions it answers

Namequota measures your brand's share of AI answers. Paste what ChatGPT, Perplexity, Google AI Mode or Claude answered to a buyer question, with its source links, and see whether the answer named you and linked you.

Send up to 50 answers at once and get mention share and citation share, such as 0 of 8, split by engine and by buyer prompt. A buyer prompt is a question that does not already name you, so a mention there was earned. If an engine repeats the question, that echo does not count.

Add your rivals to see who the answers name instead. The tool lists the sites engines cite in the answers that skip you, with their page type, and turns that into a short list of pages to write or places to get listed.

It scores the text you send. It does not ask any AI engine and it does not fetch the links, so it never scrapes ChatGPT, Perplexity, Google or Claude. Answers are not stored.

What it can do

• Mention share and citation share of a brand across up to 50 AI answers
• Split by engine and by buyer prompts that do not name the brand
• Ignores a prompt the answer repeats, so an echo is not a mention
• Counts how often each named rival is named and linked
• Lists the sites engines cite instead, with a short fix list
• Scores pasted text only: no engine call, no fetch, nothing stored

Tools

• score_answer_share, Score brand share in AI answers. Call this whenever a user pastes one or more answers from ChatGPT, Perplexity, Google AI Mode, Claude or another AI assistant and asks whether the answers named or linked their brand, what share they got, which rivals or sites the answers chose instead, or what to do about it. Pass the brand, its domain, rival names and every answer in answers (each with its prompt, engine and source links). Returns mention share and citation share (such as 0 of 3), split by engine and for buyer prompts (prompts that do not name the brand), how often each rival is named, the sites cited instead and a short fix list. Fixed rules: a repeated prompt is not a mention, and a link counts only if it goes to the brand domain. It scores pasted text only and never queries an AI engine.

Add Namequota in ChatGPT

ChatGPT does not read a local config file. A custom MCP server is added in the product, and only after developer mode is on. These steps were checked against OpenAI's plugin connect guide and the ChatGPT MCP guide on 2026-10-01. Developer mode can be hidden by a workspace policy, so a Team or Enterprise admin may have to allow it first.

1. Open ChatGPT settings, then Security and login, and turn on Developer mode.
2. Open ChatGPT plugins and select the plus button.
3. Enter a name such as "Namequota" and a one-line description of what you want it to answer.
4. Under Connection, choose the public endpoint and paste https://answershare.openkrill.app/mcp. Include the /mcp path. Do not add a tunnel id: this server is already public.
5. Create the connection and review the tools ChatGPT lists. You should see score_answer_share. The feedback tools on the same server are optional and not required for the lookup.
6. Start a new conversation, add the connection from the tools menu, and ask: Did this ChatGPT answer name or link acme.com? Here is the answer and its sources.

No API key and no OAuth client id are required. The server answers without a login. Calls are limited per network and per day, and a limit comes back as a tool error rather than a partial answer. If the tool list is stale after a server change, open the connection and select Refresh, then start a new conversation.

The ChatGPT desktop app, Codex CLI and IDE extension share a different config. In the desktop app, open Settings, then MCP servers, choose Add server, select Streamable HTTP, and paste the same URL. In ~/.codex/config.toml the equivalent is a table named mcp_servers.answer-share with url = "https://answershare.openkrill.app/mcp". ChatGPT on the web does not read that file. A published directory listing is also a different path: this page is the developer-mode connection, not a claim that Namequota is already in the ChatGPT directory.

Treat the server as untrusted until you have read a few answers. A remote MCP server sees the arguments the model sends. Namequota is read-only and documents what it sends onward on the privacy page.

If it does not work

A call checked on 2026-10-11

A made-up answer about a made-up brand. The tool reads only this text, calls no AI engine, opens no link and keeps nothing. The request below was posted to https://answershare.openkrill.app/mcp as tools/call. HTTP 200. Source: the Namequota server, read 2026-10-11.

{
  "method": "tools/call",
  "params": {
    "name": "score_answer_share",
    "arguments": {
      "brand": "Acme CRM",
      "domain": "acme.com",
      "prompt": "best CRM for a small sales team",
      "answer": "For a small sales team, HubSpot is the usual pick. Pipedrive suits pipeline-heavy teams. Acme CRM is a simpler option.",
      "links": [
        "https://www.g2.com/categories/crm",
        "https://www.hubspot.com/products/crm"
      ]
    }
  }
}

• by engine. 1 returned
• answers. 1 returned
• recommendations. 2 returned

Repeat the call yourself if you need a newer reading. Cached answers expire. A rate limit is not a result: wait and try again. Nothing in the call is a ranking, a filing, or advice.

Using it in production

Nothing to install and nothing to run: no package, no Python or Node.js version and no environment variable. Namequota runs on our servers, and your client only needs the URL https://answershare.openkrill.app/mcp.

Use it in other apps

• Namequota in Claude
• Namequota in Cursor
• Namequota in VS Code
• Namequota in Pi

Frequently asked questions

Words on this page

• MCP (Model Context Protocol) definition
• Streamable HTTP transport definition
• Tool primitive definition
• Rate limit policy definition

Source: plugin listing for answer-share in this repository, and a live tools/call on 2026-10-11. As of 2026-10-11.