Pull change requests from your Amendor board into your coding agent to build and open PRs.
Scored across 4 tools
Each tool has a clear and distinct role: listing, fetching details, updating status, and attaching a preview URL. Even though set_preview_url also marks a request as ready for review, the descriptions clearly delineate the intended use, so no two tools are ambiguous.
Tools follow a mostly consistent get/list/set/update + noun snake_case pattern. update_status is slightly less specific than the others (it omits the 'change_request' object), but the overall naming convention is uniform and readable.
Four tools is a focused, well-scoped set for a change-request management workflow. Each tool serves a distinct step in the build and review process without unnecessary redundancies or bloat.
The set covers the full lifecycle of a change request from an agent's perspective: discover what users want, get full details, push the work forward with a preview URL, and update the status as it moves. Since change requests are created by end users, lacking a create tool is appropriate. No obvious gaps exist.
Get full detail for one change request so you can implement it: the user request, the exact element they pointed at (CSS selector + outerHTML), the page URL, and a screenshot URL. Call this before making the change.
Inputs: id (required). Returns: id, code, status, elements, +7 more
List change requests submitted by end users on sites you ship. Optionally filter by status. Start here to see what people are asking for.
Inputs: status. Returns: requests
Attach a deploy-preview URL to a change request and mark it ready for the requester to review.
Inputs: id (required), url (required). Returns: code, status, review_url
Update a change request status as it moves through the build and review flow.
Inputs: id (required), status (required). Returns: code, status
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Assign Linear, Jira or GitHub issues to an AI coding agent team that plans, builds, reviews, tests.
Hosted coding agent: start, follow up on and stop tasks that can open GitHub pull requests.
Let your coding agent read and write your product boards, plans and tasks in Fulveo.
Autonomous AI developers on your own infrastructure: assign a task, get a pull request.
Add one secure layer between your agents and this server.
