US energy benchmark prices from the EIA open-data API. Omit series for a one-call snapshot of every benchmark; pass series for its recent time series. Benchmarks: wti_crude / brent_crude ($/barrel), henry_hub_gas ($/MMBtu), gasoline_regular / diesel ($/gallon), electricity_retail (cents/kWh). Eac...
AI agents call energy.prices to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and retrieves historical energy price data from a public API. It has no write, execute, destructive, or financial capabilities—it simply reads benchmark information. The pay-per-call settlement model does not affect the tool's function itself. Severity is low as misuse would only result in unnecessary API calls, not data compromise or unintended consequences.
From the tool's definition Tool retrieves US energy benchmark prices from EIA open-data API; returns observational data (date, value, units, frequency) with no modification, deletion, or side effects. Operations are 'snapshot' or 'recent time series' queries.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
US energy benchmark prices from the EIA open-data API. Omit series for a one-call snapshot of every benchmark; pass series for its recent time series. Benchmarks: wti_crude / brent_crude ($/barrel), henry_hub_gas ($/MMBtu), gasoline_regular / diesel ($/gallon), electricity_retail (cents/kWh). Each observation has date, value, units, frequency. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for energy.prices: 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 Mcp. Nothing to install.
energy.prices 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 energy.prices 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 energy.prices. 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.
energy.prices is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →