Skip to content
MCP server

Layero

Deploy and operate sites on Layero, a hosting platform with build servers in Russia

Install
Platforms
Web, API, CLI
Runs
Remotely
Version
2.4.0
Listing updated
1 day ago

About Layero

Layero is an MCP server for cloud and infrastructure. It runs as a hosted remote server, so there is nothing to install locally.

The docs describe three situations an agent can be in. If the project is linked to a Git repository, deploying is a push (a branch gives a preview, main gives production). If there is only a code folder, the CLI deploys it with npx layero@latest deploy --json, building on the platform side. If the site already exists, the MCP tools diagnose failed builds, show logs, roll back, connect and check domains, manage environment variables, read analytics and use the Data API.

Without signing in, search_docs, check_copy and refactor_site are available; the rest needs OAuth or a LAYERO_TOKEN bearer token for CI. Tools that change a live site require confirmation, and the docs say agents should never guess a site's address, always use the one the platform returns.

The documentation is in Russian. The README says Layero supports repositories on GitHub, GitVerse, GitLab, GitFlic and SourceCraft, with preview branches, custom domains and Postgres with a Data API.

Install

Run in a terminal

claude mcp add --transport http layero https://mcp.layero.ru/mcp

Add to Settings → Connectors → Add custom connector

https://mcp.layero.ru/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "layero": {
      "url": "https://mcp.layero.ru/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "layero": {
      "type": "http",
      "url": "https://mcp.layero.ru/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "layero": {
      "serverUrl": "https://mcp.layero.ru/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "layero": {
      "type": "http",
      "url": "https://mcp.layero.ru/mcp"
    }
  }
}

Tools this server provides (13)

Taken from the project documentation; the running server may differ.

search_docs
Search the documentation
check_copy
Check site copy
refactor_site
Refactor a site
publish_site
Publish a static folder
diagnose_deploy
Diagnose a failed build
deploy_logs
Read deployment logs
rollback
Roll back a deployment
connect_domain
Connect a domain
check_domain
Check a domain
env_vars
Manage environment variables
site_analytics
Read site analytics
site_status
Show site status
my_projects
List projects

What it does

Three deployment paths
Git push, folder deploy via CLI, or operating an existing site.
Diagnostics and rollback
Diagnose failed builds, read logs and roll back.
Domains and env
Connect and check domains and manage environment variables.
Site analytics
Read analytics for a deployed site.
Data API
Work with Postgres through a Data API.
Confirmation for changes
Tools that change a live site ask for approval.

Good for

  • Publish a static site from a folder
  • Find out why a build failed
  • Roll back a bad release
  • Connect a custom domain
  • Set environment variables for a site

Layero FAQ

Which tools work without signing in?

search_docs, check_copy and refactor_site.

How does CI authenticate?

With a LAYERO_TOKEN as a bearer token.

Can I connect a repo from the CLI or MCP?

Not yet, the docs say repository connection is done in the dashboard.

What language are the docs in?

Russian.

How do I add Layero to Claude Code?

Run this command in your terminal: claude mcp add --transport http layero https://mcp.layero.ru/mcp

What are the best alternatives to Layero?

The closest alternatives to Layero are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Layero

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools