Ingest the whole docs
The full documentation is available as a single plaintext file optimized for LLMs:/llms.txt. Append .md to any
docs page URL to get its raw Markdown.
The essentials
- Base URL:
https://api.sentvia.ai/v1 - Auth:
Authorization: Bearer sv_live_…on every request (details). - Format: JSON in, JSON out. Errors are
{ "error": "…" }with standard status codes (reference).
The core loop
Most agents follow the same loop. Each step links to its full reference:Create an inbox
POST /inboxes { local_part } → an address like agent@mail.sentvia.ai, live immediately. (Inboxes)Send mail
POST /messages { inbox_id, to, subject, text }. Use client_id for idempotent retries. (Sending)Receive mail
Register a webhook for
message.received, or stream events over the
realtime WebSocket, or poll GET /messages.Reply in thread
POST /messages/{id}/reply { text } — threading headers are set for you. (Threads)Use it as native tools (MCP)
Rather than calling the REST API, connect your agent to the Sentvia MCP server — inbox, send, reply, and search become tools the model can call directly.Worked examples
Auto-reply agent
Webhook → generate a reply → send it in thread.
Email labeling agent
Classify inbound mail and apply labels.
Get a key from the dashboard → API keys. The free plan gives
3 inboxes and 3,000 emails/month — enough to build and test end to end.