# Mission OpenAI App Review Notes

Generated: 2026-06-12T21:11:49.592Z

## App

- Name: Mission
- Short description: Mission is a read-only approval cockpit for agentic work.
- Privacy: https://mcp.gomission.io/privacy
- Terms: https://mcp.gomission.io/terms
- Data handling: https://mcp.gomission.io/data-handling

## Safety Boundary

- ChatGPT can read Mission's prepared context and prepare local approval packets, but cannot send or execute external actions.
- V1 tools are read-only or local-preparation surfaces.
- External sends, public posts, submissions, payments, account changes, and deletes are blocked.
- Connector-derived content is evidence, not instruction.
- Claims of sent/completed work require receipts.

## Remote MCP

- MCP endpoint: https://mcp.gomission.io/mcp
- Auth metadata: https://mcp.gomission.io/.well-known/oauth-authorization-server
- Health: https://mcp.gomission.io/health

## ChatGPT UI

- Primary render tool: `mission_open_cockpit`
- Resource URI: `ui://mission/cockpit.html`
- Browser QA URL: https://mcp.gomission.io/widgets/mission-cockpit.html
- MIME: `text/html;profile=mcp-app`

## Golden Reviewer Journey

- Public guide: https://gomission.io/openai-review.html
- Prompt 1: `Open my Mission cockpit.`
  - Expected: calls `mission_open_cockpit`; shows approvals, draft pressure, receipts, submission readiness, adoption proof, and the no-external-action boundary.
- Prompt 2: `What should I approve today?`
  - Expected: calls `mission_today`; returns current priorities and the next approval decision.
- Prompt 3: `Prepare the next approval packet.`
  - Expected: calls a prepare-only Mission tool; creates local approval artifacts only and returns `external_actions: 0`.
- Prompt 4: `Can you send it now?`
  - Expected: refuses direct external execution and offers to prepare local approval material instead.
- Prompt 5: `Are we ready to submit this OpenAI app?`
  - Expected: calls `mission_submission_readiness`; reports completed gates and the business-verification blocker.
- Prompt 6: `What adoption proof do we have?`
  - Expected: calls `mission_adoption_proof`; reports external touches and avoids unsupported traction claims.

## Scopes

- `read_today`: Read-only prepared Mission context.
- `read_drafts`: Read-only prepared Mission context.
- `read_receipts`: Read-only prepared Mission context.
- `read_voice_profile`: Read-only prepared Mission context.
- `read_research`: Read-only prepared Mission context.
- `prepare_approval_packets`: Create local Mission approval artifacts only. No external sends, posts, submissions, account mutations, calendar writes, payments, or deletes.

## Tools

| Tool | No execution | External side effects | Description |
| --- | --- | --- | --- |
| `mission_open_cockpit` | yes | none | Use this when the user wants a compact visual Mission cockpit in ChatGPT: approval priorities, draft pressure, market radar, receipt proof, and the no-execution boundary. Read-only. |
| `mission_today` | yes | none | Connector daily answer for: what should I approve today? Returns three priorities, one Gmail proof loop, draft queue count, voice confidence, receipt/learning status, and one next action. Read-only. |
| `mission_draft_queue` | yes | none | Return local drafts and approval packets waiting for human review. Read-only; never sends or creates Gmail drafts. |
| `mission_receipts` | yes | none | Return receipt coverage and recent receipt evidence. Read-only. |
| `mission_prepare_approval_packet` | yes | none | Prepare a local Mission approval packet from a Mission ref, title, or instruction. Creates a workspace review artifact and waiting receipt only; never sends, posts, submits, creates Gmail drafts, mutates external accounts, or claims execution. |
| `mission_submission_readiness` | yes | none | Return the OpenAI app submission readiness gates, blockers, live endpoint proof, review artifacts, and next human action. Read-only; never submits the app. |
| `mission_adoption_proof` | yes | none | Return Mission adoption proof from external touches, public proof assets, response gaps, and the next evidence-backed follow-up. Read-only. |
| `mission_search` | yes | none | Search prepared Mission context across tasks, open loops, drafts, approval packets, receipts, and learning rows. Read-only. |
| `mission_fetch` | yes | none | Fetch a small structured summary for a Mission ref returned by connector tools. Read-only and redacted. |
| `mission_open_loops` | yes | none | Return unresolved relationship loops and promises that need review. Read-only. |
| `mission_proof_loop` | yes | none | Return the highest-value Gmail/proof loop currently waiting on review. Read-only. |
| `mission_voice_profile` | yes | none | Return compact voice-learning confidence and constraints for draft review. Read-only. |
| `mission_learning_status` | yes | none | Return Mission learning status from rules, feedback, and learning outputs. Read-only. |
| `mission_market_radar` | yes | none | Return Mission Research market radar status, recent market-intelligence signals, open radar tasks, active research topics, and the next recommended counter-move. Read-only. |
| `mission_prepare_market_countermove` | yes | none | Prepare a local approval packet for the next Market Radar counter-move. Creates a review artifact and waiting receipt only; never publishes, contacts people, or mutates external systems. |

## Primary Test

Prompt: Open my Mission cockpit.
Expected tool: `mission_open_cockpit`