Text Embeddings turns a sentence, paragraph or short document into a 384-dimension vector that captures its meaning, ready for semantic search, clustering, deduplication and recommendations. Send one text or a batch of up to 32, and add a compare text to get the cosine similarity of each one to it in the same call.
Enable Text Embeddings and it becomes a tool your agent calls over MCP to check itself against live data before it answers — grounding the response instead of guessing.
Text Embeddings rides the one VerveContext MCP endpoint alongside 300+ other sources, so adding it to an agent is a toggle, not an integration.
The agent pulls text embeddings at answer time and can carry the source with the result, so the reasoning stays current and auditable.
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.
modeldimensionsnormalizedembeddingcharacterssimilarityHow to ground an agent in it over MCP.
Same data, same VerveContext account, same credit balance — one key works on all of them.
