MCP App Store
by KeenEthics
Forge AI Accountability icon

Forge AI Accountability MCP Server for ChatGPT

By Forge Orbital

Overview

Try a small slice of Forge Orbital's accountability engine: compare an agent's baseline with a proposed change, explore cost options, and check a sample decision with a recorded, replayable result. EVALUATE AND OPTIMIZE Use the built-in fictional vendor-payment workflow to compare labeled baseline and candidate results. See missed reviews, regressions and changed tool paths. Explore illustrative cost options before making a change. Results apply only to the evidence supplied; synthetic estimates are not realized savings. No external agent runs and no change is applied. GOVERN Choose a fictional decision scenario, inspect the evidence, run a check, then verify and replay the returned record. Remove evidence or edit a record to see the checks respond. No generative model sits in Forge Orbital's decision path. FROM TRIAL TO FULL INTEGRATION Repeat the sample comparisons as you explore. Full integration brings ongoing evaluation, optimization and governance to your own evidence, policies and workflows, in your approved environment. The demo does not connect to customer systems or approve real actions. Do not enter confidential information, personal data, credentials or production records. Questions and integration: joseph@forgeorbital.com

How to connect

  1. ChatGPT: Open the Forge AI Accountability listing in the ChatGPT app directory and choose Connect. ChatGPT listing Forge AI Accountability exposes 7 tools here.

Tools

explain_verdict

ChatGPT
Explains, in plain English, why Forge Orbital reached the verdict in a demo decision record and what evidence a reviewer would need to change it. Read-only, stateless, demo data only.

get_attestation_summary

ChatGPT
Verifies a Forge Orbital demo decision record against the pinned demo key and summarizes what it attests: signature status, the decision, whether the engine abstained, whether human review is required, and how many evidence items were used. Does not store the record. Demo records only.

list_scenarios

ChatGPT
Lists the five sample scenarios for the fictional Acme Mutual Insurance that run_check accepts, with their evidence ids. Demo data only.

replay_decision_record

ChatGPT
Replays a Forge Orbital demo decision: re-runs the deterministic engine on the same sample scenario (and any withdrawn evidence) and checks that the replay key and the decision match the record. Replayability is the point: the same inputs and engine version give the same decision. Reads nothing about the user. Demo only, fictional sample data.

review_agent_workflow

ChatGPT
Run the Forge evaluator and optimizer on synthetic examples or supplied labeled baseline/candidate outputs and token usage. Use payload={sample_mode: improved}, regression, or changed_path for examples. A description alone returns an integration plan, not a measured evaluation. No code runs, external agent calls, changes or deployment. Synthetic prices are unsigned estimates, never approved savings. Interactive version: https://demo.forgeorbital.com/lab

run_check

ChatGPT
Computes a Forge Orbital verdict for one of five fictional Acme Mutual Insurance scenarios and returns it with a signed decision record in the response. Read-only: nothing is stored, sent or changed. Optionally withdraw evidence ids to see how the verdict changes. Demo only: sample rules and sample evidence, not connected to the user's systems, policies or live actions.

verify_decision_record

ChatGPT
Verifies the Ed25519 signature of a Forge Orbital demo decision record against the published demo key id. Pass the full signed record object returned by run_check (this demo keeps nothing, so a record id alone cannot be looked up). Editing any field makes verification fail. Demo records only.

Capabilities

Interactive

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/forge-ai-accountability"><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/forge-ai-accountability)