Is the Layero MCP server down?

mcp-registry/ru.layero/layero · v2.5.0

Also listed as github/layeroinfra/layero-agents

healthy
Last checked 2026-10-24 09:22 UTC · handshake 853ms

As of 2026-10-24 09:22 UTC, the Layero MCP server is up with a Glimind reliability score of 79/100 (grade B). Over the last 30 days it answered 99.7% of Glimind's liveness checks. It had 36 outages in 90 days, with a median recovery of 3 minutes.

uptime (30d checks)
99.7%
checks observed
4,390
outages (90d)
36
tools
36

Deploy and operate sites on Layero — hosting with build servers in Russia: domains, env, Data API.

Install Layero MCP server

Add to Cursor Add to VS Code

Claude Code

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

Claude Desktop · Windsurf · Cline (mcpServers JSON)

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

Third-party server, listed as discovered. Review its source before installing.

Agent-readiness: A (91/100)

A (91/100): 0 error(s), 2 warning(s) across 36 tool(s); ~13,409 tokens of tool definitions.
Scores higher than 72% of 15,635 MCP servers Glimind has audited.
Its tool list costs an agent ~13,409 tokens per session — more than 85% of servers.
87 → 91 since 2026-10-17
no tool-poisoning patterns
Schemas100
Descriptions100
Safety hints53
Token cost100
Client compatibility100
Protocol100
Reliability85
Stability100

What to fix (3)

6 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.

Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →

Tools: cancel_deploy, deploy_logs, diagnose_deploy, publish_landing, publish_site and 1 more

Handshake + tools/list takes ~3,191 ms.

Serve tools/list from memory, keep the process warm, and host close to your users. Every new agent session pays this before its first call.

7 of 36 tool(s) carry no readOnlyHint/destructiveHint annotations.

Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →

Tools: cancel_deploy, connect_analytics, connect_domain, import_repo, publish_landing and 2 more

Auto-fix: 5 corrected tool definitions

Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fru.layero%2Flayero/fixes

cancel_deploy 1 change
{
  "name": "cancel_deploy",
  "description": "Stop a build that is still running.\n\n    The live address does not change — the previous version stays on it.\n    ",
  "inputSchema": {
    "type": "object",
    "title": "cancel_deployArguments",
    "required": [
      "project"
    ],
    "properties": {
      "deploy": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Deploy",
        "default": null,
        "description": "Build id (a UUID from `list_deploys`). Without it the latest build is used."
      },
      "project": {
        "type": "string",
        "title": "Project",
        "description": "The project: its slug (`my-site`) or id, as listed by `my_projects`. The site address works too (`https://clear-garden-vypm.layero.app` or just `clear-garden-vypm`) — note that the address host is NOT always the slug."
      }
    }
  },
  "annotations": {
    "openWorldHint": true,
    "readOnlyHint": false,
    "destructiveHint": true,
    "idempotentHint": true
  },
  "title": "Отменить идущую сборку"
}
import_repo 1 change
{
  "name": "import_repo",
  "description": "Create a Layero project from a repository — path (a) without the\n    dashboard. From then on a push to the branch is a preview, a push to the\n    production branch is production.\n\n    After the link the tool finishes the setup wizard itself and starts the\n    first build; `setup` in the result says whether that happened. Detected\n    values are NOT written into the project settings: the builder detects\n    the framework, build command and output folder from the repository on\n    every build, so ",
  "inputSchema": {
    "type": "object",
    "title": "import_repoArguments",
    "required": [
      "provider",
      "repo"
    ],
    "properties": {
      "name": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Name",
        "default": null,
        "description": "Project name; the slug and the address are derived from it. Defaults to the repository name — for a second app from the same monorepo give a distinct name."
      },
      "repo": {
        "type": "string",
        "title": "Repo",
        "description": "Repository path at the provider: `owner/repo`; GitLab paths may be nested (`group/sub/project`). The form `gitverse:owner/repo` is accepted too."
      },
      "branch": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Branch",
        "default": null,
        "description": "Production branch. Defaults to the repository's default branch."
      },
      "deploy": {
        "type": "boolean",
        "title": "Deploy",
        "default": true,
        "description": "Finish the setup wizard and start the first build right away. The framework, build command and output folder are not pinned: the builder detects them from the repository on every build (`layero.json` overrides). `false` leaves the project in the setup wizard: no builds until the person completes the setup in the dashboard."
      },
      "provider": {
        "type": "string",
        "title": "Provider",
        "description": "Provider: github, gitverse, gitlab, gitflic or sourcecraft."
      },
      "organization": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Organization",
        "default": null,
        "description": "Organization slug. Without it — the account's only organization, or the personal one; if there are several and none is personal, the tool lists the slugs."
      },
      "root_directory": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Root Directory",
        "default": null,
        "description": "Monorepo: the app folder inside the repository, relative to its root — `apps/web`, `frontend`. Omit it for an app in the repository root (if the root has no app and exactly one subfolder does, that folder is picked automatically). A repository already linked to a project can be imported again ONLY with a `root_directory` that no linked project uses."
      }
    }
  },
  "annotations": {
    "openWorldHint": true,
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false
  },
  "title": "Проект из репозитория"
}
publish_landing 1 change
{
  "name": "publish_landing",
  "description": "DEPRECATED — use `publish_site`. Same behaviour, same arguments.\n\n    Kept for one release (removed in the next) so that configs and prompts\n    written before 17.09.2026 keep working; new instructions must call\n    `publish_site`.\n    ",
  "inputSchema": {
    "type": "object",
    "$defs": {
      "FilePayload": {
        "type": "object",
        "title": "FilePayload",
        "required": [
          "path",
          "content"
        ],
        "properties": {
          "path": {
            "type": "string",
            "title": "Path"
          },
          "content": {
            "type": "string",
            "title": "Content"
          },
          "encoding": {
            "enum": [
              "text",
              "base64"
            ],
            "type": "string",
            "title": "Encoding",
            "default": "text",
            "description": "Use `base64` for binary files — images, fonts, favicons. Text files (html/css/js/svg) stay `text`. A binary sent as text is silently corrupted."
          }
        }
      }
    },
    "title": "publish_landingArguments",
    "required": [
      "files",
      "project_name"
    ],
    "properties": {
      "files": {
        "type": "array",
        "items": {
          "$ref": "#/$defs/FilePayload"
        },
        "title": "Files",
        "description": "Same as in `publish_site`: the site files with `index.html` in the root."
      },
      "project": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Project",
        "default": null,
        "description": "Same as in `publish_site`: id of an existing project."
      },
      "project_name": {
        "type": "string",
        "title": "Project Name",
        "description": "Same as in `publish_site`: the project slug."
      }
    }
  },
  "annotations": {
    "openWorldHint": true,
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false
  },
  "title": "Опубликовать сайт (старое имя)"
}

Get alerted

Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:

curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/ru.layero/layero"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/ru.layero/layero"}) over MCP.

Passed

Largest tool definitions

Static checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).

Operator? Fix these, then re-check live. Embed the readiness badge:

Markdown
[![MCP agent-readiness](https://glimind.com/v1/readiness/badge/mcp-registry%2Fru.layero%2Flayero.svg)](https://glimind.com/server/mcp-registry%2Fru.layero%2Flayero?ref=badge)
HTML
<a href="https://glimind.com/server/mcp-registry%2Fru.layero%2Flayero?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fru.layero%2Flayero.svg" alt="MCP agent-readiness"></a>
reStructuredText
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fru.layero%2Flayero.svg
   :target: https://glimind.com/server/mcp-registry%2Fru.layero%2Flayero?ref=badge
   :alt: MCP agent-readiness

Tool-definition log

Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:607f59a43e44376b…, first seen 2026-10-17, included at leaf 10240 of 57,950. Version history · verify what your client received.

Tools (36)

Compare: most reliable devops servers · most reliable data servers · most reliable security servers · most reliable web servers · most reliable database servers

Know before your agent calls it

Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.

Add Glimind — free, no signup:

Add to Cursor Add to VS Code

Claude Code

claude mcp add --transport http glimind https://glimind.com/mcp

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "glimind": {
      "type": "http",
      "url": "https://glimind.com/mcp"
    }
  }
}

FAQ

Is the Layero MCP server down right now?

As of 2026-10-24 09:22 UTC, the Layero MCP server is up with a Glimind reliability score of 79/100 (grade B). Over the last 30 days it answered 99.7% of Glimind's liveness checks. It had 36 outages in 90 days, with a median recovery of 3 minutes.

How many tools does Layero MCP server provide?

Layero MCP server advertises 36 tools, including cancel_deploy, check_copy, check_domain, check_performance, check_rules.

How do I install Layero MCP server?

Point your MCP client at this streamable-http endpoint: https://mcp.layero.ru/mcp

Is the Layero MCP server safe to connect to an AI agent?

Glimind scanned all 36 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.

Operator of Layero MCP server?

Status page: 90-day uptime, every outage and how long it lasted.

Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.

Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.

Feedback
Help us improve