Ground agents in official weekly fuel price surveys from the EIA, the European Commission and the UK government, so cost answers track the real pump.
An agent asked about prices or rates will happily invent a figure. Enable Gas Price and it calls the gasprices tool to check the live number before it answers — so the reply rests on real data, not the model's memory.
Give a market assistant a source it can actually cite: every figure it reports carries Gas Price as its origin, so a human can trace where the number came from.
Because the model pulls gas price at the moment it responds, the answer reflects the market now — not whatever was true when the model was trained.
Point your agent framework at the VerveContext endpoint. Every enabled source — this one included — becomes a tool the model can call. No per-source plumbing.
{
"mcpServers": {
"vervecontext": {
"url": "https://api.vervecontext.com/v1/mcp",
"headers": { "x-api-key": "vc_live_••••" }
}
}
}Each call returns structured fields your agent can read — and trace back to this source.
countrycountryNameareaareaNameareaTypeweekcurrencyunitHow to ground an agent in it over MCP.
Same data, same VerveContext account, same credit balance — one key works on all of them.
