← Registry

Content Tools

shpt.ai

Allows users to publish, list, update, and delete websites or content on shpt.ai.

1 endpoint4 known toolsFirst detected May 13, 2026Last detected June 30, 2026

ENDPOINT 1

https://www.shpt.ai/mcp

No auth detected

Known tools 4

publish

Publish content to shpt.ai and get a live URL instantly.

Potential side effects
list_sites

List all sites published under the current token.

Inferred read-only
update_site

Update content or metadata of a published site.

Potential side effects
delete_site

Delete a published site and all its files.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.shpt-ai]
url = "https://www.shpt.ai/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "shpt-ai": {
      "type": "http",
      "url": "https://www.shpt.ai/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: shpt-ai
Remote MCP URL: https://www.shpt.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "shpt-ai": {
      "url": "https://www.shpt.ai/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "shpt-ai": {
      "type": "http",
      "url": "https://www.shpt.ai/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "shpt-ai",
  "transport": "streamable-http",
  "url": "https://www.shpt.ai/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for shpt.ai was fetched 2026-08-03T23:18:34.311Z and is being refreshed.

Trust status Neutral

shpt.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.