DevOps
justpublish.ai
This MCP server enables you to deploy and manage live websites by publishing, reading, and updating site files.
ENDPOINT 1
https://mcp.justpublish.ai
MCP server metadata
- Name
- Just Publish
- Version
- 0.1.8
Publish the website you built with AI to a live public URL — straight from chat, no setup.
Known tools 3
get_site_filesRead the files of a site you already published, so you can make a targeted edit instead of rebuilding the whole site from memory.
Potential side effectsupdate_site_fileChange one or a few files of an already-published site, leaving every other file untouched (a merge — unlike deploy, which replaces the whole site).
Inferred read-onlyCONNECT 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.just-publish]
url = "https://mcp.justpublish.ai"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"just-publish": {
"type": "http",
"url": "https://mcp.justpublish.ai"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: just-publish
Remote MCP URL: https://mcp.justpublish.ai
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": {
"just-publish": {
"url": "https://mcp.justpublish.ai"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"just-publish": {
"type": "http",
"url": "https://mcp.justpublish.ai"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "just-publish",
"transport": "streamable-http",
"url": "https://mcp.justpublish.ai"
}
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 justpublish.ai was fetched 2026-07-26T05:04:01.399Z and is being refreshed.
justpublish.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.