Temporal Invoice Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Temporal Invoice Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
uv (curl -LsSf https://astral.sh/uv/install.sh | sh) git clone https://github.com/your-org/temporal-mcp-invoice-demo.git
cd temporal-mcp-invoice-demo
uv venv
source .venv/bin/activate
uv pip install temporalio fastmcp temporal server start-dev python worker.py [--fail-validate] [--fail-payment]Instead of starting the server and worker manually you can launch them in a tmux session using the boot-demo.sh helper script:
./boot-demo.sh{
"mcpServers": {
"invoice_processor": {
"command": "/Path/To/Your/Install/Of/uv",
"args": [
"--directory",
"/Path/To/temporal-invoice-mcp",
"run",
"server.py"
]
}
}
}invoice_processor under 'Search & Tools'trigger <paste: samples/invoice_acme.json>Use your MCP client (e.g., Claude Desktop) to call the trigger, approve, reject, and status tools. The trigger tool now returns both the workflow_id and run_id of the started workflow. Pass these values to the approve, reject, and status tools. The sample invoice lives at samples/invoice_acme.json. Inspect Temporal Web at http://localhost:8233. Kill and restart the worker at any time to observe deterministic replay.
Claude submits the invoice workflow:
<img src="./assets/claude-mcp-invoice-submission.png" width="50%" alt="Claude MCP Invoice Submission" style="display: block; margin: auto;">
It can get status:
<img src="./assets/claude-mcp-invoice-status.png" width="50%" alt="Claude MCP Status" style="display: block; margin: auto;">
Claude + MCP can send inputs and updates to the process workflow such as approvals, or even do a combination of actions - all agentically, explaining in human analogies what's going on if you ask it to:
<img src="./assets/claude-mcp-submit-approve-status.png" width="50%" alt="Claude MCP Combo" style="display: block; margin: auto;">
<img src="./assets/interactive-workflows-with-agentic-power.png" width="80%" alt="Interactive Agentic Applications Powered By Workflows" style="display: block; margin: auto;">
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.