Back to search
manufact-leaderboard
MCP serverGitHub
GitHub Action: rescan your MCP server on the Manufact leaderboard after each deploy and report its score
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked today
Badge for your README
Markdown
[](/listings/mcp-use--manufact-leaderboard)HTML
<a href="/listings/mcp-use--manufact-leaderboard"><img src="/api/listings/mcp-use--manufact-leaderboard/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 53 lines
- # Manufact Leaderboard
- Rescan your MCP server on the [Manufact leaderboard](https://manufact.com/leaderboard) after every deploy, wait for the review, and get the new score in the run summary.
- The server must be verified by your workspace first: open its leaderboard page and choose **Verify**. Only the verifying workspace can rescan it.
- ## Usage
- Add a `MANUFACT_API_KEY` repository secret with an API key from that workspace, then add a step after your deploy:
- ```yaml
- - name: Manufact Leaderboard
- uses: mcp-use/manufact-leaderboard@v1
- with:
- api-key: ${{ secrets.MANUFACT_API_KEY }}
- url: https://mcp.example.com/mcp
- ```
- The step prints the score and a report link, and writes them to the job summary. A rescan that can't start, fails, or runs past the timeout leaves a warning and never fails your deploy, unless you set `fail-on-error: true`.
- ## Inputs
- | Input | Default | Description |
- | --- | --- | --- |
- | `api-key` | required | Manufact API key from the workspace that verified the server. |
- | `url` | required | The server's MCP endpoint URL, as listed on the leaderboard. |
- | `wait` | `true` | Wait for the rescan and report the score. `false` only starts it. |
- | `timeout-minutes` | `10` | How long to wait for the rescan. |
- | `fail-on-error` | `false` | Fail the step when the rescan can't start or fails. |
- | `api-url` | `https://api.manufact.com` | Manufact API base URL. |
- | `site-url` | `https://manufact.com` | Manufact website base URL, for the report link. |
- ## Outputs
- | Output | Description |
- | --- | --- |
- | `score` | Score out of 100 after the rescan. |
- | `status` | `completed`, `failed`, `running` (timed out) or `started` (`wait: false`). |
- | `slug` | The server's leaderboard slug. |
- | `report-url` | Link to the server's leaderboard report. |
- Use the score in a later step, for example to comment on a pull request:
- ```yaml
- - id: leaderboard
- uses: mcp-use/manufact-leaderboard@v1
- with:
- api-key: ${{ secrets.MANUFACT_API_KEY }}
- url: https://mcp.example.com/mcp
- - run: echo "Score ${{ steps.leaderboard.outputs.score }} - ${{ steps.leaderboard.outputs.report-url }}"
- ```
- The action uses `bash`, `curl` and `jq`, which GitHub-hosted runners include.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.