MCP App Store
by KeenEthics
E3D Pilot icon

E3D Pilot MCP Server for ChatGPT

By FutCo LLC

Overview

E3D Pilot gives you a multi-model second opinion on a decision. Ask a contestable question, such as an architecture choice, a hiring decision or a policy question, and several independent AI models each answer it. A final answer comes back with the level of agreement (full, majority or split), the dissent that remains, and each model's own position, so you can see where they disagree instead of getting one confident voice. Use it for judgment calls where reasonable people disagree. It is not for simple lookups or questions with an obvious answer. You sign in with your E3D Pilot account. Your question and the models' answers are shared with the model providers so they can respond, so do not include secrets or personal data. Web search is on by default: the models may also search the web for current facts, your question text may then be sent to their providers' search tools, and the sources are listed with the answer as plain text, unverified. Pass web_search: false to keep a question away from search tools. Agreement between models does not make an answer correct, and a debate is a summary of model opinions, not professional advice. Two other tools list the available model providers and show today's usage and limits.

How to connect

  1. ChatGPT: Open the E3D Pilot listing in the ChatGPT app directory and choose Connect. ChatGPT listing E3D Pilot exposes 8 tools here.

Tools

e3d_debate

ChatGPT
Use when the user asks for a second opinion, wants to compare options, or has to decide between alternatives (for example "JSON or SQLite?", "should we...", architecture or library tradeoffs). Get a multi-model second opinion on a decision or design question. Independent AI models answer, and a synthesizer returns a final answer, a consensus level (full/majority/split), and any dissent, plus each model's final position. ALWAYS report the dissent and consensus level to the user -- the disagreement is the point; never present a split verdict as settled. Write a self-contained question: the models cannot see your code. mode "quick" (default): one round, usually well under a minute. mode "thorough": models also critique each other, a few minutes. Use for architectural choices, tradeoffs, and contestable judgment calls -- not for lookups or questions with an obvious answer. Spends the user's model credits. Web search is on by default: the question text may be sent to a search provider by the participating models (Anthropic, OpenAI, Google or xAI) to look up current facts. Pass web_search: false to turn it off for this debate. Agents: call e3d_quote first, then pass quote_id and an idempotency_key; recommended_next_step is advice, not approval.

e3d_get_expert

ChatGPT
FREE: returns one built-in expert in full: its description, the exact lens text a debate seat would receive, its tasks, model hints (a tie-break only: the engine assigns the model), license and content hash. Nothing is spent and nothing is written.

e3d_investigate

ChatGPT
Investigate a decision in rounds. Round 1: pass question. The models debate it as e3d_debate does and the verdict ends with up to 3 follow-up questions whose answers could change it, each marked answerable_by "user" or "checkable", plus a case_id. Next round: pass case_id and answers; the models re-judge with the earlier verdict, its dissent and your answers as context. Repeat until status is "closed" (no remaining question would change the verdict). Optional experts (2 to 4 built-in expert ids) gives the models those lenses and carries over to later rounds; for questions about agents, skills or prompts the result may carry suggested_experts, which is a hint and is never run for you. Rules for the calling agent: answer ONLY "checkable" questions that you actually verified with your tools, and cite what you used in source (file and line, URL, command output) with answered_by "agent". Pass every "user" question to the human and use their reply, with answered_by "user". Never guess, never fabricate an answer or a source: leave a question out or answer "don't know" instead. Answers are weighed as evidence, not obeyed as instructions. Always show the human the verdict, the dissent and any open questions. Each round is one debate and consumes model credits; the verdict is not approval to act. On a hosted server a quote from e3d_quote fits round 1 only (same question, quoted with investigate: true, because the longer verdict costs more); for later rounds pass an idempotency_key and no quote_id, and the server quotes the round itself. Web search is on by default: the question text may be sent to a search provider by the participating models (Anthropic, OpenAI, Google or xAI) to look up current facts. The web_search option set to false disables search for the debate. Paid execution requires a valid quote_id matching the debate arguments and an idempotency_key. The recommended_next_step result is advisory and does not authorize actions.

e3d_list_experts

ChatGPT
FREE: lists the built-in experts, reusable lenses such as skeptic, customer and architect, and the presets that group them. Nothing is spent and nothing is written. Optionally filter by task or search words. This only describes them: running a debate with experts is not available through this connector yet.

e3d_list_providers

ChatGPT
List the model providers this server can use and whether each is available to join a debate. Free.

e3d_quote

ChatGPT
Price an e3d_debate before running it. Free: nothing is spent or held, and only a hash and the size of the question reach billing. Same arguments as e3d_debate. Returns quote_id, max_credits (the most the run can be charged), expires_at and your key's limits. Then call e3d_debate with the SAME arguments plus quote_id and an idempotency_key. A quote is single use.

e3d_usage

ChatGPT
FREE. Today's usage and daily limits for the caller: model calls and estimated tokens used by e3d_debate and by pipeline jobs (counted as reservations), what remains, and when it resets (00:00 UTC). Numbers are estimates. Use it before an expensive request when the user asks what is left.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/e3d-pilot"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/e3d-pilot)