tengu_v3_intel_ml_prediction
Latest ensemble ML prediction for the ticker, with full conformal interval + 19-voter decomposition. Sourced from the nightly ensemble scoring run (refreshed nightly Mon-Fri, ~13K tickers scored per cycle). Returns prediction block (predicted_return_pct, blended_score, conviction, decile, rank, p...
This record as markdown: /tools/tengu-mcp/tengu-v3-intel-ml-prediction.md
What tengu_v3_intel_ml_prediction does on Tengu
AI agents invoke tengu_v3_intel_ml_prediction 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
ticker | string | Yes | Path parameter 'ticker' (required). |
asset_class | string | — |
Parameters from the server's own tool schema.
Why tengu_v3_intel_ml_prediction is rated High
tengu_v3_intel_ml_prediction 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.
Attacks that exploit this kind of access
The rule that runs tengu_v3_intel_ml_prediction safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Tengu, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For tengu_v3_intel_ml_prediction, this is the rule to start with:
tengu_v3_intel_ml_prediction stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Tengu, apply this rule, and every tengu_v3_intel_ml_prediction call is checked against it from then on.
Questions about tengu_v3_intel_ml_prediction
Latest ensemble ML prediction for the ticker, with full conformal interval + 19-voter decomposition. Sourced from the nightly ensemble scoring run (refreshed nightly Mon-Fri, ~13K tickers scored per cycle). Returns prediction block (predicted_return_pct, blended_score, conviction, decile, rank, percentile_rank, n_universe), conformal_interval block (lo/hi/half_width/method + stated_coverage 0.90 + realised_coverage_recent from live calibration table), voter_decomposition (per-voter contribution across the 19 voters — e.g. ml_ensemble, regime_hmm, technical_advanced, sentiment_finbert, macro_context, fundamental, options_flow, insider_flow, analyst_revisions, futures_macro, congress_trading, short_pressure), context (voter_coverage, confluence, feature_coverage), plus model_version, tier (small/mid/large universe), regime, sector. When a ticker isn't in the latest scoring universe, returns available: false with reason. 5min cache. NAMESPACE: predictions are US-EQUITY only. Nine crypto tickers collide with equities (BTC, ETH, LINK, LTC, COMP, ARB, NEAR, APT, ATOM) — such responses carry a ticker_collision note; for the crypto asset pass asset_class=crypto (fails closed 404: no crypto model yet). NEVER present an equity prediction as a crypto view. It is categorised as a Execute tool in the Tengu MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
tengu_v3_intel_ml_prediction accepts 2 parameters: ticker, asset_class. Required: ticker. The full parameter table on this page comes from the server's own tool schema.
Register the Tengu MCP server in PolicyLayer and add a rule for tengu_v3_intel_ml_prediction: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Tengu. Nothing to install.
tengu_v3_intel_ml_prediction is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the tengu_v3_intel_ml_prediction rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for tengu_v3_intel_ml_prediction. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
tengu_v3_intel_ml_prediction is provided by the Tengu MCP server (Hlobo-dev/tengu-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Tengu, and thousands of servers like it.
Across the catalogue