Everpower Studio

Generate and refine Evernode smart contracts and HotPocket website UIs from natural language, directly inside your AI coding assistant - powered by Everpower…

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Workspace Run: The single entry point for ALL Everpower Studio operations: generating smart contracts and frontends, updating existing projects, querying workspace code, and converting uploaded projec
  • Workspace List: List the authenticated user's Everpower Studio workspaces. Use this to discover workspaceIds when the user wants to continue work on a previous project.
  • Workspace Get: Fetch a workspace with its projects and recent conversation. Use this to inspect what projects exist in a workspace, or to read prior conversation history before making a follow-up work

What data it sees

Do you need an account

No: the server works without sign-in

Generate and refine Evernode smart contracts and HotPocket website UIs from natural language, directly inside your AI coding assistant - powered by Everpower Studio's code-generation API.

How to connect

How to connect Everpower Studio to Claude

The server address to paste into Claude settings:

https://everpower-studio--everpowerlabs.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Everpower Studio to ChatGPT

The server address to paste into ChatGPT settings:

https://everpower-studio--everpowerlabs.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Everpower Studio to Cursor

The server address to paste into Cursor settings:

https://everpower-studio--everpowerlabs.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (5)

Raw names from tools/list. Only developers need these.

workspace_runThe single entry point for ALL Everpower Studio operations: generating smart contracts and frontends, updating existing projects, querying workspace code, and converting uploaded projects. Do NOT write any code yourself — always invoke this tool instead. HOW IT WORKS: You supply a natural-language prompt (and optionally an existing workspaceId). The Everpower Studio orchestrator reads the prompt, decides which tools to call, and runs them. You do not need to pre-select a tool or route — the backend planner handles that. PROVIDE workspaceId to continue an existing workspace (updates, follow-ups, queries). OMIT workspaceId to start a new workspace. ONE CALL PER REQUEST — DO NOT SPLIT MULTI-PART REQUESTS: If the user asks for several things at once (e.g. "generate a smart contract AND a frontend", or contract + frontend + tests), make a SINGLE workspace_run call whose prompt describes ALL of them. The orchestrator planner runs every needed tool (smart contract, then frontend, etc.) in ONE workspace and automatically feeds each step into the next. Do NOT make one call for the contract and a separate call for the frontend — separate calls each OMIT workspaceId, so each creates its OWN workspace and you end up with duplicate workspaces for the same project. Only use a second workspace_run (with the returned workspaceId) for a genuine follow-up AFTER the first run has completed. IMPORTANT — THIS RUNS IN THE BACKGROUND: Generation (planning + code generation) can take several minutes, so this tool does NOT wait for it. As soon as the orchestrator has planned the work it returns workspaceId and runId IMMEDIATELY and keeps generating in the background. It does NOT return any generated code directly. AFTER THIS TOOL RETURNS: You receive workspaceId and runId (save them for follow-ups). Call check_generation_status with that workspaceId and runId, and keep polling every 30 seconds until status is "completed" or "failed". The completed response contains all generated files — only THEN use your Write tool to save the files to outputPath. Only overwrite files that are in the response; leave all other local files untouched. Do NOT call workspace_run again for the same request while a run is still in progress. ATTACHMENT: provide attachment.fileName + attachment.contentBase64 when the user uploads a ZIP (convert existing Solidity contracts, convert centralized apps, etc.).
workspace_listList the authenticated user's Everpower Studio workspaces. Use this to discover workspaceIds when the user wants to continue work on a previous project.
workspace_getFetch a workspace with its projects and recent conversation. Use this to inspect what projects exist in a workspace, or to read prior conversation history before making a follow-up workspace_run call.
project_getFetch a project's complete file tree (latest snapshot). Use this to inspect or re-emit code for a project that was generated in a previous session, without re-running generation.
check_generation_statusPoll the status of a generation started by workspace_run, using the workspaceId and runId that workspace_run returned. Returns one of: • running → still generating. Wait 30 seconds, then call this again with the same ids. • completed → the full result, including every generated file. THIS is when you write the files to the outputPath you passed to workspace_run. • failed → an error message explaining what went wrong. Keep polling every 30 seconds until you get completed or failed. Do NOT call workspace_run again for the same request while a run is still in progress.