← ManufactCONTENT HISTORY

Update to Manufact

Snapshot Oct 24, 2026 · 12:57 UTC · version 2.1.0

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save Manufact and check future changes in Following.

Up to 3 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Use when a user wants to know whether their MCP server or MCP app is ready to publish to ChatGPT, Claude, or another app directory, wants to run or fix the Manufact publishing checklist, test the server with evals, or prepare submission assets such as screenshots, a demo video, and submission metadata.",
  "included_files": [
    {
      "relative_path": "references/checklist-checks.md",
      "size_in_bytes": 5744
    },
    {
      "relative_path": "references/submission-pack.md",
      "size_in_bytes": 2768
    }
  ],
  "name": "manufact-publish-ready",
  "skill_md_contents": "---\nname: manufact-publish-ready\ndescription: Use when a user wants to know whether their MCP server or MCP app is ready to publish to ChatGPT, Claude, or another app directory, wants to run or fix the Manufact publishing checklist, test the server with evals, or prepare submission assets such as screenshots, a demo video, and submission metadata.\nmetadata:\n  owner: manufact\n---\n\n# Get an MCP server ready to publish\n\nApp directories such as the ChatGPT app directory and Claude's connector\ndirectory reject servers for protocol errors, missing tool metadata, broken\nwidgets, and policy problems. Manufact finds these before a reviewer does.\n\n\"Ready\" means:\n\n- the server is deployed and healthy,\n- the publishing checklist has no blocking failures for the target platform,\n- the server behaves correctly in real clients, and\n- the submission assets exist.\n\nWork through the steps below in order. Checklist runs, eval runs, and\nsubmission packs consume credits, so fix everything you can find for free\nbefore spending them.\n\n## 1. Pick the server and target\n\n1. Find the server with `list_organizations`, `list_servers`, and `get_server`.\n   The server must have a live deployment. If it doesn't, use the\n   `manufact-deploy` skill first.\n2. Ask which platforms the user is targeting: ChatGPT, Claude, or both. The\n   answer decides which failures matter.\n3. Check whether a run already exists with `list_checklist_runs`. If a recent\n   run matches the current deployment, read it with `get_checklist_run` instead\n   of starting a new one.\n\n## 2. Review the code first (free)\n\nIf you can read the server's source, check it against the common blocking\nfailures before running anything. See\n[references/checklist-checks.md](references/checklist-checks.md) for the full\nlist.\n\n- **Every tool has a top-level `title` and a description.**\n- **Every tool sets boolean `readOnlyHint`, `destructiveHint`, and\n  `openWorldHint`.** The values must match what the tool actually does.\n- **Tool names are unique, at most 64 characters, and use only letters, digits,\n  `_`, `-`, or `.`.**\n- **Input schemas are objects.** Declared output schemas are valid.\n- **For MCP apps with widgets:**\n  - Each widget resource uses a `ui://` URI with the MIME type\n    `text/html;profile=mcp-app`.\n  - It declares one exact HTTPS domain.\n  - Its CSP lists every external origin it loads or connects to.\n- **Listings don't overpromise.** Descriptions and behavior avoid policy\n  problems: misleading claims, collecting sensitive data without need, and\n  unexpected destructive actions.\n\nFix what you find, commit, push, and let the deployment finish before\ncontinuing.\n\n## 3. Authenticate protected servers\n\nIf the server requires OAuth, the checklist needs credentials to connect.\n\n1. Call `authenticate_deployment` with `serverId`. Pass `branch` only for a\n   preview. Give the user the returned `authenticationUrl` as a clickable link.\n2. After the user says they're done, call it again with the returned\n   `sessionId`.\n3. Only `authenticated` means success. `pending` means the user hasn't\n   finished. `expired` or `failed` means you need a new link.\n4. Never ask the user for OAuth credentials, tokens, or passwords.\n\n## 4. Run the publishing checklist\n\n1. **Confirm with the user before starting.** Each call starts a new billed run.\n   On the Hobby plan and above, it also runs the paid end-to-end checks in real\n   ChatGPT and Claude sessions.\n2. Call `run_publishing_checklist` with `serverId`. Omit `branch` to check\n   production.\n3. **Read the run with `get_checklist_run`** and the returned `runId`. Runs take\n   several minutes. `completed` and `failed` are final; `pending` and `running`\n   mean the run is still in progress.\n   - If the start response was lost or uncertain, look at\n     `list_checklist_runs` before starting another run.\n4. **Read the final result:**\n   - `isReadyForChatgpt` and `isReadyForClaudeai`: a platform is ready when no\n     check with severity `error` fails for it. Warnings and info never block.\n   - `score`: a 0–100 quality signal that matches the dashboard. It is not the\n     readiness verdict.\n   - A `failed` run means the checklist itself couldn't finish, for example\n     because the server was unreachable or authentication failed. It says\n     nothing about the server's quality. Fix the cause before rerunning.\n5. **Report back grouped by priority:**\n   1. Blocking errors for the user's target platforms.\n   2. Warnings worth fixing.\n   3. Everything else, briefly.\n\n   Quote each failing check's `message` and `hint`. On the Free plan, `message`,\n   `details`, and `hint` are usually `null`. In that case, explain the check\n   from the reference file and mention that the dashboard's Checklist tab (and\n   upgrading) give full fix guidance.\n\n## 5. Fix and verify\n\n- **Fix issues in the server's code**, using the hints and\n  [references/checklist-checks.md](references/checklist-checks.md). Then push and\n  let the deployment finish. With a connected repository, the dashboard can also\n  open an autofix pull request.\n- **Rerun the checklist once** after the fixes are live. Don't rerun until\n  something has changed.\n- Automatic runs after each deployment are available through\n  `update_server_checklist_settings`. They cost credits too, so enable them only\n  when the user asks.\n\n## 6. Test real behavior with evals\n\nChecklist checks look at metadata. Evals check whether models actually pick the\nright tools and give useful answers.\n\n1. Call `get_eval_options` and `list_eval_models` to see available clients and\n   models.\n2. Call `create_eval_suite` with a realistic conversation, the tools the model\n   should call, and passing criteria.\n3. Call `run_eval_suites` after the user confirms (each run uses a credit).\n4. Read the results with `get_eval_report`. Walk through the judge findings for\n   any failed client or model.\n\nEvals always target the production endpoint.\n\n## 7. Let people try it\n\nA public chat page lets anyone try the server in a browser, with no MCP client\nneeded. It requires the Hobby plan or higher.\n\n- Check the current state with `get_public_chat_configuration`.\n- Enable it with `configure_public_chat`: `enabled: true`, a title, and up to\n  eight suggested questions that show off the main tools.\n\n## 8. Generate the submission pack\n\nGenerate the pack after the checklist is clean for the target platform. See\n[references/submission-pack.md](references/submission-pack.md) for the full flow.\n\n- `generate_submission_pack` produces three components for the production\n  server:\n  - submission metadata JSON,\n  - a desktop demo video, and\n  - up to four screenshots.\n- The pack is billed and requires the Hobby plan or higher. Confirm with the\n  user first.\n- Generation keeps running after the call returns. Use `get_submission_pack` to\n  check on it and to get `downloads`. Save each file into the user's project:\n  fetch the video and screenshot URLs, and write the inline submission JSON to\n  its file.\n- Share the `dashboardUrl` so the user can review and submit.\n"
}

SHA-256 of public snapshot: b4c49d9e4236bf9be3a92ff7103beb64c95d7bccc5924f1d2b592706e3792bed