Skip to main content
v3 shares the platform’s transport protections and has these operational bounds:
  • one MCP connection remains open for at most 30 minutes;
  • one tool call is limited to 30 minutes;
  • deploys may interrupt long in-flight work after the drain window;
  • structured responses over 200 KB are truncated as a safety backstop; and
  • request_proposals durably enumerates the marketplace and returns running; each background seller attempt has a 90-second bound, or 5 minutes for a seller that acknowledges its brief with a task id within those 90 seconds, and result pages are byte- and count-bounded.
Calls that start a model turn are capped per account. The Murph chat, chat stream and conversation message endpoints (under /murph and /apostra) allow 30 requests a minute per account in production; past that the API answers 429, so wait a minute and retry. Reads and other Murph endpoints are not counted. Tools that run a model count against the same 30 calls a minute per account. Today that is generate_variants. Past the limit the call returns a RATE_LIMITED error, so wait a minute and retry. Every other tool is unaffected. Use returned cursors, keep pages small, and preserve partial results. A retry must reuse an idempotency key only when it represents the same logical attempt. Upstream seller and inventory systems can dominate latency even when the v3 facade itself is healthy.

Full rate-limit reference

Review the canonical HTTP and MCP rate-limit behavior and retry guidance.