One Click for ChatGPT
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@One Click for ChatGPTTurn this business brief into a structured handoff for Lovable"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
One Click for ChatGPT
One Click converts a small set of task-specific website requirements into a structured handoff for the separately installed Lovable plugin. This repository is intentionally separate from the existing One Click website.
Capability boundary
Current release: no-account, ephemeral Basic Mode website handoff.
One Click tool: prepares the brief only. It does not create, publish or deploy a website and it does not persist the business brief.
Lovable: a separate external write path used only after the user authorises project creation.
Later release: authenticated saved projects and Full Mode remain outside the exposed tool catalogue until reviewed independently.
Related MCP server: @metricspot/mcp-server
MCP
Production endpoint: https://oneclick-chatgpt.woeinvests.workers.dev/mcp
Tool:
oneclick_prepare_basic_draft
Required inputs are only industry and primary_goal. Optional inputs are limited to business_name, brand_vibe, headline, call_to_action, layout and services. The API rejects unexpected properties, wrong types, unsupported layouts and oversized requests. It does not accept full conversation history, inferred location, generic catch-all notes or reference-image URLs.
Tool annotations
oneclick_prepare_basic_draft explicitly declares:
readOnlyHint: falsebecause a minimal operational analytics event may be appended for each tool invocation.destructiveHint: falsebecause it does not delete or overwrite customer state.openWorldHint: falsebecause it does not browse arbitrary URLs or invoke external services.
Analytics Engine records only tool name, success/error, rounded latency, release version and coarse client family. Application-level analytics deliberately exclude prompt text, business brief content, business names, URLs, project IDs, tokens, IPs, raw headers and stable user identifiers.
Development and release
npm run check
npm run deploy:dry
npm run deploy
npm run smoke:productionProduction pushes require CLOUDFLARE_API_TOKEN and CLOUDFLARE_ACCOUNT_ID. The deployment workflow runs the full checks, deploys the Worker and then verifies the live MCP catalogue, annotations, narrowed schema, a valid call and rejection of broad input.
This server cannot be deployed
Maintenance
Related MCP Connectors
Serves your design system and coding standards to coding agents, so they stop guessing.
Publish and update HTML websites, landing pages, reports and proposals from AI chat. OAuth sign-in.
Generate MantleKit setup plans and launch-ready SaaS blueprints from a product idea.
Build, version, review, and export websites, web apps, and games from a conversation.
Related MCP Servers
- -licenseNot gradedqualityNot gradedmaintenanceEnables automated project analysis and structured development specification generation. Supports multiple export formats and integrates with AI models for comprehensive project documentation and validation.-

@metricspot/mcp-serverofficial
AlicenseNot gradedqualityFmaintenanceExposes SEO and AI-readability audit tools to AI agents, enabling one-shot anonymous audits or full authenticated audits with PDF reports and organic traffic data.45 npmMIT- AlicenseBqualityDmaintenanceEnables AI coding assistants to extract screenshots, DOM content, and structured frontend analysis from public links, including Axure prototypes.21MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to vet a developer's shipped products, check fixed pricing and availability, and submit project briefs on behalf of users.1MIT