tengu_v3_intel_commodities
REAL-TIME spot prices for the macro commodities (oil WTI/Brent, gold, silver, nat-gas, copper). AUTHORITATIVE source for any numeric commodity claim — call this BEFORE quoting a price level. QUOTE 'spot' DIRECTLY — it's the live commodity price (FRED's last published close anchored to the live co...
This record as markdown: /tools/tengu-mcp/tengu-v3-intel-commodities.md
What tengu_v3_intel_commodities does on Tengu
AI agents call tengu_v3_intel_commodities to retrieve information from Tengu without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
symbol | string | — |
Parameters from the server's own tool schema.
Why tengu_v3_intel_commodities is rated Low
Even though tengu_v3_intel_commodities 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.
Attacks that exploit this kind of access
The rule that runs tengu_v3_intel_commodities 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_commodities, this is the rule to start with:
tengu_v3_intel_commodities is read-only, so it stays allowed. 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_commodities call is checked against it from then on.
Questions about tengu_v3_intel_commodities
REAL-TIME spot prices for the macro commodities (oil WTI/Brent, gold, silver, nat-gas, copper). AUTHORITATIVE source for any numeric commodity claim — call this BEFORE quoting a price level. QUOTE 'spot' DIRECTLY — it's the live commodity price (FRED's last published close anchored to the live commodity-tracking ETF's cumulative return since that date, so it reflects today's market not FRED's T+1..T+5 publish lag). 'unit' tells you the dimension (USD/barrel for oil, USD/MMBtu for natgas, USD/metric-ton for copper). Response fields per item: 'spot' (live number — quote this), 'unit' (dimension), 'spot_basis' ('live_etf_bridged' = FRED+ETF bridge | 'fred_close' = FRED only, no ETF available | 'etf_share_price' = FRED dead, falling back to ETF SHARE price [unit reads 'USD per share of {ETF}'] — DO NOT claim $/oz when basis is etf_share_price), 'spot_time' (timestamp of the live observation), 'live_spot_estimate' (same as spot when bridged, else null), 'live_basis' (transparent arithmetic, e.g. 'FRED WTI $99.89 (2026-04-27) × (USO 142.80 / 134.72)'), 'bridge_return_pct' (ETF return applied to FRED), 'official_close' + 'official_close_as_of' (FRED audit value — quote ONLY if user explicitly asks for the last settlement / closing price), 'change_pct_1d/5d/30d' (FRED-window returns), 'history_5d' (last 6 FRED observations newest-first), 'fred_days_stale' + 'is_stale' (publish-lag flags — informational; spot is still live regardless), 'etf_proxy_quote' (the underlying ETF snapshot used for the bridge; for transparency only). 'symbol=oil' returns both WTI and Brent; default 'all' returns all six. It is categorised as a Read tool in the Tengu MCP Server, which means it retrieves data without modifying state.
tengu_v3_intel_commodities accepts 1 parameter: symbol. 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_commodities: 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_commodities is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the tengu_v3_intel_commodities 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_commodities. 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_commodities 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.
This server
Across the catalogue