deplo.sh

Deploy static sites, files, and JSON APIs instantly from any AI agent.

Community: Submitted by a user or imported; check the owner before granting accessOnlineAPI key requiredGlobalFreeRead-only

What it can do

  • Deployments Create: Deploy files to deplo.sh and get a live public URL. Auto-creates the project when project_slug is new or omitted. Returns the deployment URL, version number, file count, and expiry
  • Projects List: List all projects in the workspace. Returns each project's ID, slug, type, live deployment ID, storage usage, and custom domain.
  • Projects Get: Get full details of a single project by its ID or slug, including its live deployment, custom domain status, and storage usage.

What data it sees

Do you need an account

An API key from the service settings is required

Deploy static sites, files, and JSON APIs instantly from any AI agent. No config, no infrastructure.

How to connect

How to connect deplo.sh to Claude

The server address to paste into Claude settings:

https://deplo.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 deplo.sh to ChatGPT

The server address to paste into ChatGPT settings:

https://deplo.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 deplo.sh to Cursor

The server address to paste into Cursor settings:

https://deplo.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 (15)

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

deployments_createDeploy files to deplo.sh and get a live public URL. Auto-creates the project when project_slug is new or omitted. Returns the deployment URL, version number, file count, and expiry date.
projects_listList all projects in the workspace. Returns each project's ID, slug, type, live deployment ID, storage usage, and custom domain.
projects_getGet full details of a single project by its ID or slug, including its live deployment, custom domain status, and storage usage.
deployments_listList all deployment versions for a project, ordered newest-first. Use this to find deployment IDs for rollback (deployments.promote) or cleanup (deployments.archive).
deployments_promotePromote an older deployment version to become the live version (rollback). The deployment's public URL will immediately serve the promoted version's files. Use deployments.list to find the deployment ID you want to roll back to.
projects_deletePermanently delete a project and ALL its deployments. This action cannot be undone. Confirm with the user before calling.
projects_createCreate a new empty project in the workspace. Prefer deployments.create when you also have files to deploy — it auto-creates the project and deploys in one step.
projects_updateUpdate one or more project settings: display name, custom domain, password protection, or default TTL. Only fields you provide are changed; omitted fields are left unchanged. After attaching a custom domain call domain.verify to check DNS propagation.
domain_verifyCheck whether the DNS CNAME record for a project's custom domain is correctly pointing to proxy.deplo.sh. Returns verification status and the actual CNAME values found. Call this after attaching a domain via projects.update.
deployments_getGet full details of a specific deployment version, including status, file count, storage size, entry path, and expiry date.
deployments_archiveArchive an old deployment version to free up storage. The archived deployment's files are deleted and it can no longer be promoted. Do not archive the currently live deployment.
account_meReturn information about the currently authenticated API key: workspace ID, granted permission scopes, and any project-level scope restriction. Useful for verifying which key is in use and what it is allowed to do.
tokens_listList all API access tokens in the workspace. Returns each token's ID, name, scopes, and expiry date. Raw token values (sk_live_…) are never returned after creation.
tokens_createCreate a new API access token. The raw token value (sk_live_…) is returned only once — save it immediately. Tokens can be scoped to a single project and given an expiry date for least-privilege access.
tokens_revokePermanently revoke an API access token by its ID. Any request using the revoked token will immediately receive a 401. This action cannot be undone. Use tokens.list to find the token ID (not the sk_live_… value).