Ground agents in verifiable word definitions so language answers cite a real dictionary source instead of paraphrased memory.
Let an agent call Dictionary to expand an ID into full, structured detail from live data — grounding enrichment steps in fact, not recall.
Wire dictionary into an agent so it pulls the fields it's missing at the moment it needs them, each traceable to the source.
Every detail the agent adds carries Dictionary as its origin, keeping the pipeline verifiable.
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.
worddefinitionCountdefinitionsHow to ground an agent in it over MCP.