Cowork scheduled task and paid Sume tools: use dry_run, max_spend_usd
Cowork asks for an approval mode when you schedule a task, and tasks run while your computer is asleep. Put dry_run and max_spend_usd on every paid Sume call.

When you schedule a task in Claude Cowork, you choose an approval mode as part of setup, and the task then runs remotely even when your computer is asleep. The help page does not detail what each mode asks for, so I will not guess. What you can control regardless of the mode is what the Sume call itself will accept: dry_run=true previews a paid create without submitting it, and max_spend_usd caps it when sent.
Scheduling behavior is from Claude's Cowork scheduled tasks article, read on 2026-10-03; the paid-tool parameters are in Sume's MCP tools and gates.
What does the schedule page promise?
Tasks run on a schedule you set and, per the article, run remotely, so a closed laptop does not stop them. Because nobody is watching, whatever approval mode you pick is the only human check in the loop. Choose it knowing which tools the task will touch.
What do Sume's paid tools require?
Paid and write tools need an idempotency_key. dry_run and max_spend_usd are optional, and max_spend_usd is enforced only when you provide it. generation_admission_preview shows what admission would say before a burst. If the connection was authorized with mcp:read only, none of the paid tools are callable.
| Parameter | Required? | What it does |
|---|---|---|
idempotency_key | Yes, paid and write | Makes a retry safe |
dry_run | No | Previews without submitting |
max_spend_usd | No | Caps spend, only when sent |
What should the task prompt say?
- First call with
dry_run=trueand report the estimate. - Proceed only if the estimate is under a number written in the prompt.
- Send
max_spend_usdset to that number and a freshidempotency_key. - Do not retry a failed paid call with a new key; reuse the old one.
Where does this leave the approval mode?
The mode decides whether a person sees each step; the parameters decide what a step can cost. Use both. A strict mode with no cap still depends on someone reading carefully, and a cap with no approval still lets a task do work you did not intend, only cheaper.
If you only need a read, authorize the connection with mcp:read and skip the issue. That scope is required on every session, write is opt-in, and the consent screen has Write off by default. A task that only looks up job status or results does not need more, and a paid call from it would return insufficient_scope instead of spending.
Sources
Related posts
More in Integrations
- Claude Desktop Code tab subagents lose a "memory" MCP server
Claude Code 2.1.288 fixed subagents in the Claude Desktop Code tab getting no tools from a user MCP server named memory. Why Sume stays named sume.
- Claude Desktop managed connector OAuth client change and Sume
Claude Desktop 2.110 stops connecting managed connectors that have their own OAuth client but no credentials. Sume requires sign-in either way.
- Claude Desktop mcpToolTimeoutSec 180 s: does Sume jobs_wait fit?
Claude Desktop 2.110 added mcpToolTimeoutSec, default 180 seconds. Sume jobs_wait holds at most 55 seconds, so the default fits with room to spare.
- Claude managed MCP connector redirect error: Sume final URL
Claude Desktop managed MCP connections stopped following HTTP redirects and now report a configuration error. Give Sume's endpoint exactly: mcp.sume.com/mcp.
Written by Sume