Ground agents in verifiable city data — population, country and coordinates across 150K+ places — so location answers rest on real records, not guesses.
Give an agent City so it resolves places, distances, and timezones from real data instead of approximating — the difference between a plausible answer and a correct one.
When a user names a location, the agent calls citieslookup to confirm and normalize it before acting, closing off a common source of silent errors.
Every location fact the agent uses carries City as its origin, so the reasoning is auditable end to end.
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.
searchfoundCitiesHow to ground an agent in it over MCP.
