# get_scoring_rules

Fetch the live winner/loser bar the scorer actually enforces: minimum ROAS and purchases for a winner (both must clear in the same window), the loser impression floor, and the maturity period before any verdict. Served from the scoring module itself, so it stays correct when the owner moves a dial - these numbers have already moved twice. Call it instead of assuming a threshold.

Agent View of the PolicyLayer registry record for `get_scoring_rules`. HTML page: https://policylayer.com/tools/577-tools-ad-lab-mcp/get-scoring-rules

## Facts

- Tool: `get_scoring_rules`
- Server: Ad Lab (`@577-tools/ad-lab-mcp`) — https://policylayer.com/tools/577-tools-ad-lab-mcp.md
- Install: `npx -y @577-tools/ad-lab-mcp`
- Homepage: https://www.npmjs.com/package/@577-tools/ad-lab-mcp
- Risk category: Read (Low risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_scoring_rules",
    "arguments": {}
  }
}
```

## Why get_scoring_rules is rated Low

Even though get_scoring_rules only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

## Use case

AI agents call get_scoring_rules to retrieve information from Ad Lab without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Ad Lab:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_scoring_rules": {}
  }
}
```

## Other tools on Ad Lab (12)

- `advance_stage` — Read — https://policylayer.com/tools/577-tools-ad-lab-mcp/advance-stage.md
- `get_creative` — Read — https://policylayer.com/tools/577-tools-ad-lab-mcp/get-creative.md
- `get_flow_status` — Read — https://policylayer.com/tools/577-tools-ad-lab-mcp/get-flow-status.md
- `get_knowledge_index` — Read — https://policylayer.com/tools/577-tools-ad-lab-mcp/get-knowledge-index.md
- `get_lab_capacity` — Read — https://policylayer.com/tools/577-tools-ad-lab-mcp/get-lab-capacity.md
- `get_product_context` — Read — https://policylayer.com/tools/577-tools-ad-lab-mcp/get-product-context.md
- `list_external_winners` — Read — https://policylayer.com/tools/577-tools-ad-lab-mcp/list-external-winners.md
- `list_losers` — Read — https://policylayer.com/tools/577-tools-ad-lab-mcp/list-losers.md
- `list_revision_requests` — Read — https://policylayer.com/tools/577-tools-ad-lab-mcp/list-revision-requests.md
- `list_winners` — Read — https://policylayer.com/tools/577-tools-ad-lab-mcp/list-winners.md
- `render` — Read — https://policylayer.com/tools/577-tools-ad-lab-mcp/render.md
- `add_idea` — Write — https://policylayer.com/tools/577-tools-ad-lab-mcp/add-idea.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=577-tools-ad-lab-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/577-tools-ad-lab-mcp