Product videos from a chat agent: dry run first, then submit
Higgsfield added slash commands in ChatGPT. When an agent makes product videos on Sume's hosted MCP, preview with dry_run, then submit with a key.

When a chat agent makes product videos through Sume's hosted MCP server, have it call the paid tool with dry_run=true first, read the estimate, then repeat the call without it and with a fresh idempotency_key. Higgsfield's changelog says its ChatGPT extension (2026-09-30) offers slash commands /effects, /product, and /genjutsu. Sume has no slash-command layer; the agent calls MCP tools instead.
Tool and gate facts are from Sume's MCP tools and gates page, read 2026-10-02; the Higgsfield line is from its changelog.
What does the agent call?
generate_video creates the job (it replaced the retired video-router_create alias), then jobs_wait and jobs_result return the output. tools_list and tools_schema tell the agent the live contract, and the docs say not to assume parity with the HTTP API. To connect a ChatGPT workspace to a remote server, see How to add an MCP server to ChatGPT.
Which safety gates apply?
Every write and paid tool requires an idempotency_key, which the docs call a transport and dedup key, not human approval. dry_run=true previews admission and cost without submitting. max_spend_usd is enforced only when provided. Under OAuth, paid tools stay hidden until the session has mcp:write; there is no separate paid scope.
| Gate | Required? | Meaning |
|---|---|---|
idempotency_key | Yes, on write and paid tools | Dedup key, not approval |
dry_run=true | Optional | Cost and admission preview only |
max_spend_usd | Optional | Cap, only when you pass it |
mcp:write scope | For OAuth sessions | Needed to see paid tools |
What should I tell the agent?
Put the order in its instructions: tools_schema for generate_video, a dry run, then a submit only after the user confirms the spend. The docs' own playbook for a paid avatar create uses the same order. Tell it to reuse the same idempotency_key on retries and never to resubmit a paid create after a timeout.
How long does a wait last?
A jobs_wait call can hold for up to 55 seconds, so the client's timeout must exceed that; MCP tool call timeouts on long video jobs covers the slicing pattern.
Treat the dry run as part of the conversation: the agent shows the estimate, the user says yes or no, and only then does the paid call go out. Log the idempotency key with the user's confirmation, so a retry after a dropped connection reuses the same key. If the agent cannot see paid tools, check whether the session has write scope before assuming the tool is missing.
Sources
Related posts
More in Integrations
- Qwen Code MCP server: add Sume with qwen mcp add --transport http
Add Sume's hosted MCP to Qwen Code with qwen mcp add --transport http: an API-key header, a timeout above 55 s, and include-tools to keep paid tools out.
- Raycast MCP: add Sume's hosted server with Dynamic OAuth
Add Sume to Raycast as an HTTP MCP server: URL, Dynamic OAuth sign-in, read-only by default, and when to switch to an API-key header for paid tools.
- Replit Add MCP server: connect Sume with an X-API-Key header
Replit's Add MCP server flow takes an HTTPS endpoint, optional custom headers and Test and save. Connect Sume's hosted MCP and confirm the tools load.
- Runway MCP plus Sume MCP in one Claude Code setup: who does what
Runway added four Kling models to its MCP on 2026-09-18. Here is how a client can hold Runway and Sume MCP servers together and how to split the video jobs.
Written by Sume