# tengu_v3_intel_ml_drivers

Top-N SHAP feature attributions for the ML ensemble score on a ticker: drivers[] ranked by |SHAP| with feature (e.g. beta_cma, vol_21d), signed shap_value, direction (bullish/bearish/neutral). PRIMARY tool for 'why is the model bullish/bearish on X?'. Nightly run; default top=5, max 20; available:false outside the ML universe. 5min cache.

Agent View of the PolicyLayer registry record for `tengu_v3_intel_ml_drivers`. HTML page: https://policylayer.com/tools/tengu-mcp/tengu-v3-intel-ml-drivers

## Facts

- Tool: `tengu_v3_intel_ml_drivers`
- Server: Tengu (`Hlobo-dev/tengu-mcp`) — https://policylayer.com/tools/tengu-mcp.md
- Homepage: https://github.com/Hlobo-dev/tengu-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 2 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `top` | string | no |  |
| `ticker` | string | yes | Path parameter 'ticker' (required). |

Parameters from the server's own tool schema.

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "tengu_v3_intel_ml_drivers",
    "arguments": {
      "ticker": "<ticker>"
    }
  }
}
```

## Why tengu_v3_intel_ml_drivers is rated High

tengu_v3_intel_ml_drivers triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

## Use case

AI agents invoke tengu_v3_intel_ml_drivers to trigger actions in Tengu. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Tengu:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "tengu_v3_intel_ml_drivers": {
      "limits": [
        {
          "counter": "tengu_v3_intel_ml_drivers_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Tengu (336)

- `tengu_v3_features_dataset` — Destructive — https://policylayer.com/tools/tengu-mcp/tengu-v3-features-dataset.md
- `tengu_v3_intel_borrow_cost_history` — Destructive — https://policylayer.com/tools/tengu-mcp/tengu-v3-intel-borrow-cost-history.md
- `tengu_v3_intel_insider_flow` — Destructive — https://policylayer.com/tools/tengu-mcp/tengu-v3-intel-insider-flow.md
- `tengu_v3_intel_risk_free_rate` — Destructive — https://policylayer.com/tools/tengu-mcp/tengu-v3-intel-risk-free-rate.md
- `tengu_v3_intel_sec13f_changes` — Destructive — https://policylayer.com/tools/tengu-mcp/tengu-v3-intel-sec13f-changes.md
- `tengu_v3_backtest_run_detail` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-backtest-run-detail.md
- `tengu_v3_briefing_daily` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-briefing-daily.md
- `tengu_v3_factor_predictors` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-factor-predictors.md
- `tengu_v3_intel_darkpool_history` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-intel-darkpool-history.md
- `tengu_v3_intel_gex_history` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-intel-gex-history.md
- `tengu_v3_intel_ml_prediction` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-intel-ml-prediction.md
- `tengu_v3_intel_options_flow_history` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-intel-options-flow-history.md
- `tengu_v3_news_sentiment_history` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-news-sentiment-history.md
- `tengu_v3_optimizer_latest` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-optimizer-latest.md
- `tengu_v3_prices_corporate_actions` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-prices-corporate-actions.md
- `tengu_v3_private_markets_service_provider_relations` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-private-markets-service-provider-relations.md
- `tengu_v3_reference_coverage` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-reference-coverage.md
- `tengu_v3_supply_chain_relationships` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-supply-chain-relationships.md
- `tengu_v3_tape_bars` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-tape-bars.md
- `tengu_v3_validation_trials` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-validation-trials.md
- `tengu_v3_workforce_layoffs` — Execute — https://policylayer.com/tools/tengu-mcp/tengu-v3-workforce-layoffs.md
- `tengu_cache_stats` — Read — https://policylayer.com/tools/tengu-mcp/tengu-cache-stats.md
- `tengu_copilot_decision_review` — Read — https://policylayer.com/tools/tengu-mcp/tengu-copilot-decision-review.md
- `tengu_copilot_live_ic_drift` — Read — https://policylayer.com/tools/tengu-mcp/tengu-copilot-live-ic-drift.md
- `tengu_copilot_macro_regime` — Read — https://policylayer.com/tools/tengu-mcp/tengu-copilot-macro-regime.md
- `tengu_copilot_score_ticker` — Read — https://policylayer.com/tools/tengu-mcp/tengu-copilot-score-ticker.md
- `tengu_copilot_signal_health` — Read — https://policylayer.com/tools/tengu-mcp/tengu-copilot-signal-health.md
- `tengu_copilot_ticker_full` — Read — https://policylayer.com/tools/tengu-mcp/tengu-copilot-ticker-full.md
- `tengu_copilot_ticker_smartmoney` — Read — https://policylayer.com/tools/tengu-mcp/tengu-copilot-ticker-smartmoney.md
- `tengu_copilot_ticker_transparency` — Read — https://policylayer.com/tools/tengu-mcp/tengu-copilot-ticker-transparency.md
- …and 306 more: https://policylayer.com/tools/tengu-mcp.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=tengu-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/tengu-mcp