1. Docs
2. /
3. Tool reference
4. /
5. Agents & Machines
6. /
7. setOpenPullRequestCap

Agents & Machines

setOpenPullRequestCap

Set Open PR Cap

Set the OPEN PULL REQUEST CAP on the PR rail's repositories (the ones with a deploy identity, today tekalabs/the-cloud).

write

Ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "raise the PR cap", and it calls setOpenPullRequestCap.

Example call

The MCP tools/call params, with the required arguments only.

{
  "arguments": {},
  "name": "setOpenPullRequestCap"
}

Arguments

• liftForHoursintegeroptionalLift the cap from now for this many hours; it comes back by itself. 0 ends a lift early.
• limitintegeroptionalHow many non-draft pull requests a PR rail repository may hold before a lane may not open another.

Returns

The registry does not declare a return shape.

Declared limits

• liftForHours: minimum 0
• liftForHours: maximum 24
• limit: minimum 1
• limit: maximum 500

Ask for it

The Cloud routes these requests to this verb.

• raise the PR cap
• set the open PR cap to 30
• lift the PR cap for two hours
• turn the PR cap back on
• why was my lane refused for too many open PRs

Pair it with

The verbs that finish the job.

• runAgent
• listPullRequests
• mergePullRequest

Questions

• What does setOpenPullRequestCap do?

  Set the OPEN PULL REQUEST CAP on the PR rail's repositories (the ones with a deploy identity, today tekalabs/the-cloud). It is one of the tools The Cloud MCP server gives every connected AI.

• How do I use setOpenPullRequestCap from Claude or ChatGPT?

  Connect your AI to The Cloud at https://mcp.thecloud.so/mcp and sign in once. Then ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "raise the PR cap", and it calls setOpenPullRequestCap.

• Is setOpenPullRequestCap safe to let an AI call?

  setOpenPullRequestCap changes your workspace. What an AI creates is Private until you share it.

Connect

One endpoint gives your AI this tool and every other one: connect Claude, ChatGPT, Cursor or Gemini, read what The Cloud is, or see pricing.