mcp

EU-native PaaS for AI agents — deploy web apps with one sentence, managed Postgres, GDPR by default.

¿Debería usar esto?

Calidad y seguridad

A
Calidad de la descripción
100%
Integridad del esquema
95%
Calidad de los nombres
74%
Riesgo de envenenamiento
100%
Coincidencia de permisos
100%
Cumplimiento del protocolo
100%

Hallazgos (11)

  • LOWTool 'list-projects' doesn't follow camelCase/snake_caseen list-projects
  • LOWTool 'create-project' doesn't follow camelCase/snake_caseen create-project
  • LOWTool 'delete-project' doesn't follow camelCase/snake_caseen delete-project
  • LOWTool 'get-logs' doesn't follow camelCase/snake_caseen get-logs
  • LOWTool 'set-env' doesn't follow camelCase/snake_caseen set-env
  • LOWTool 'get-env' doesn't follow camelCase/snake_caseen get-env
  • LOWTool 'get-status' doesn't follow camelCase/snake_caseen get-status
  • LOWTool 'add-domain' doesn't follow camelCase/snake_caseen add-domain
  • LOWTool 'list-domains' doesn't follow camelCase/snake_caseen list-domains
  • LOWTool 'get-domain' doesn't follow camelCase/snake_caseen get-domain

Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.

Costo de contexto

~3,829Tokens (definiciones de herramientas)
~1.1 KBTamaño de respuesta típico
Impacto significativo en la atención (2.99% del contexto de 128k)

Este es el número aproximado de tokens que se consumen cada vez que las herramientas del servidor se cargan en el contexto de un modelo. Los recuentos más altos reducen la atención disponible para otras tareas.

Instalar

Instalación con un clic

Agrega esto a tu archivo `claude_desktop_config.json`:

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "@sota-io/mcp"
      ]
    }
  }
}

Paquetes ejecutables

npm@sota-io/mcp1.5.0stdio

Puntos de conexión remotos

https://mcp.sota.io/mcpstreamable-http

Qué puede hacer

Inventario de herramientas

Herramientas (14)

🟢 Solo lectura🟡 Escritura🔴 Eliminación⚪ Desconocido
🟡create_account(email, code)

Sign up for a brand-new sota.io account from inside Claude — no browser, no copy-paste. Two-step flow: STEP 1: Call with just `email`. We send a 6-digit confirmation code to that email. STEP 2: Call again with `email` + `code`. We verify, create the account on the Free tier (3 projects, EU-hosted, no credit card), generate a sota.io API key, and return it to you. After Step 2 you'll get back a key like `sota_…`. **Save it in a safe place** — you'll need it for any subsequent sota.io tool call in Claude (or you can use it with the sota CLI). It is shown ONCE and never recoverable. sota.io is an EU-native PaaS hosted in Germany — GDPR-compliant by default, no CLOUD Act exposure. Disposable / throwaway email addresses are not accepted; use a real address.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "email": {
      "type": "string",
      "format": "email",
      "description": "A real email address. We send the confirmation code here. Throwaway / disposable email services are blocked."
    },
    "code": {
      "type": "string",
      "description": "The 6-digit code from the confirmation email. Provide on the second call to complete signup. Omit on the first call."
    }
  },
  "required": [
    "email"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list-projects

List all projects on your sota.io account. sota.io is an EU-native DevOps PaaS hosted in Germany (GDPR-compliant). Each project gets a live URL at {slug}.sota.io with automatic HTTPS, a managed PostgreSQL 17 database (DATABASE_URL auto-injected), PgBouncer connection pooling, daily backups, zero-downtime blue-green deployments, gVisor container isolation, and custom domain support (up to 5 per project with automatic HTTPS).

Esquema de entrada

{
  "type": "object",
  "properties": {}
}
🟡create-project(name, git_url, git_branch)

Create a new project on sota.io. Each project automatically provisions: (1) a managed PostgreSQL 17 database accessible via the DATABASE_URL environment variable (auto-injected, no configuration needed), (2) PgBouncer connection pooling (pool size 20, max 100 clients), (3) automatic daily database backups with 7-day retention, (4) a live URL at https://{slug}.sota.io with automatic HTTPS via Let's Encrypt. The project slug is auto-generated from the name (lowercase, hyphens, max 63 chars) and is immutable after creation. Supported frameworks: Next.js, Node.js (Express/Fastify/Koa), Python (Flask/FastAPI/Django), or any language via custom Dockerfile. You can also add up to 5 custom domains per project with automatic HTTPS (via API: POST /v1/projects/:id/domains with {domain: "yourdomain.com"}). DNS: A record to 23.88.45.28 for apex domains, CNAME to {slug}.sota.io for subdomains. Optionally associate the project with a public git repository at create-time by passing `git_url` (and optional `git_branch`). The association is informational — it shows up in the dashboard and the `sota deploy --git` CLI flag can default to it — but does NOT enable auto-deploy-on-push yet.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Name for the new project. A URL slug will be auto-generated (e.g. \"My Cool App\" becomes my-cool-app.sota.io)"
    },
    "git_url": {
      "type": "string",
      "description": "Optional git repository URL to associate with this project (https://, git://, ssh://, or git@host:path). Informational only — does not trigger an automatic deploy."
    },
    "git_branch": {
      "type": "string",
      "description": "Optional branch name (defaults to the repository default branch when omitted). Only meaningful when `git_url` is also set."
    }
  },
  "required": [
    "name"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🔴delete-project(project_id)

Delete a project and all its deployments from sota.io. This action is PERMANENT and irreversible. It removes the project, all deployments, the managed PostgreSQL database, environment variables, and webhooks. The project slug will become available again after deletion.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "project_id": {
      "type": "string",
      "description": "Project ID (UUID) to delete. Use list-projects to find the ID"
    }
  },
  "required": [
    "project_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🔴deploy(project_id, files, git_url, git_branch, directory)

Deploy an application to sota.io. The platform auto-detects your framework and builds a Docker image automatically: - Next.js: Detected via next.config.js/ts. Add output: 'standalone' to next.config for optimal builds. - Node.js: Detected via package.json with a "start" script. Works with Express, Fastify, Koa, Hapi, etc. - Python: Detected via requirements.txt or pyproject.toml. Works with Flask, FastAPI, Django. - Custom Dockerfile: If a Dockerfile exists in the project root, it takes priority over auto-detection. Use this for Go, Rust, Java, or any other language. The EXPOSE directive in the Dockerfile is used to detect the app port automatically. THREE WAYS to supply the source code — pick EXACTLY ONE: 1. **files** (inline source from AI): Pass a map of relative paths to UTF-8 text content. Best when you've just generated a small app in this conversation and want to deploy it without any filesystem step. Up to 200 files, 10 MB total. Include the framework manifest (package.json, requirements.txt, or Dockerfile) so auto-detection works. 2. **git_url** (clone a public repo): Pass an https://, git://, ssh://, or git@host:path URL. We shallow-clone it (--depth=1 --single-branch) on the server and deploy. Optional git_branch picks a non-default branch. Only public repos are supported in v1. Max 200 MB after clone. 3. **directory** (local filesystem): Pass an absolute path. Only works when the MCP client has filesystem access (Claude Code / CLI; not Claude.ai web). Defaults to the current working directory when omitted. IMPORTANT: Your app MUST listen on the PORT environment variable. For auto-detected frameworks (Next.js, Node.js, Python) PORT is 8080. For custom Dockerfiles, the port is auto-detected from the EXPOSE directive (e.g. EXPOSE 3000 sets PORT=3000). If no EXPOSE is found, it defaults to 8080. Every project includes a managed PostgreSQL 17 database. Six environment variables are auto-injected into your container — no manual database configuration needed: DATABASE_URL (full connection string), PGHOST, PGPORT, PGUSER, PGPASSWORD, and PGDATABASE. Libraries that follow libpq conventions (node-postgres, pgx, psycopg2, Django) pick up the PG* variables automatically with no configuration. If your app needs database migrations, run them on startup. Deployments use blue-green strategy for zero downtime. The old container keeps running until the new one passes health checks (60s timeout). Use get-logs to monitor build progress. Files matching .gitignore, .git/, node_modules/, .env, and .DS_Store are excluded from the archive.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "project_id": {
      "type": "string",
      "description": "Project ID (UUID) to deploy to. Use list-projects to find the ID."
    },
    "files": {
      "type": "object",
      "additionalProperties": {
        "type": "string"
      },
      "description": "Map of relative file paths to UTF-8 text content. Use when generating an app inline (e.g. from a Claude.ai web conversation). Include a framework manifest so auto-detection works. Mutually exclusive with git_url and directory."
    },
    "git_url": {
      "type": "string",
      "description": "Public git repository URL to clone (https://, git://, ssh://, or git@host:path). Mutually exclusive with files and directory."
    },
    "git_branch": {
      "type": "string",
      "description": "Optional branch name when using git_url. Defaults to the repository default branch."
    },
    "directory": {
      "type": "string",
      "description": "Absolute path to a local directory (only useful when the MCP client has filesystem access — e.g. Claude Code). Defaults to the current working directory when no other mode is given. Mutually exclusive with files and git_url."
    }
  },
  "required": [
    "project_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-logs(project_id, deployment_id)

Get build and runtime logs for a deployment. If no deployment_id is provided, returns logs for the latest deployment. Use this after calling deploy to monitor build progress and diagnose failures. Logs include: framework detection output, dependency installation, build steps, container startup, and health check results. If a deployment fails, check the logs for error details — common issues include missing dependencies, build errors, or the app not listening on the correct PORT (check the PORT env var — 8080 for auto-detected frameworks, or the EXPOSE value from Dockerfile).

Esquema de entrada

{
  "type": "object",
  "properties": {
    "project_id": {
      "type": "string",
      "description": "Project ID (UUID) to get logs for"
    },
    "deployment_id": {
      "type": "string",
      "description": "Specific deployment ID (optional, defaults to latest). Use get-status to see recent deployment IDs"
    }
  },
  "required": [
    "project_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🔴set-env(project_id, key, value)

Set an environment variable for a project. Variables are encrypted at rest (AES-256-GCM) and injected at container runtime. NOTE: DATABASE_URL, PGHOST, PGPORT, PGUSER, PGPASSWORD, and PGDATABASE are all auto-injected for the managed PostgreSQL database — you do NOT need to set any of them manually. The PORT variable is auto-managed: 8080 for auto-detected frameworks (Next.js, Node.js, Python), or auto-detected from the Dockerfile EXPOSE directive for custom Dockerfile builds. IMPORTANT: Changing env vars does NOT auto-redeploy. You must call deploy or use the redeploy API endpoint to apply changes. For Next.js apps, NEXT_PUBLIC_* variables must be set BEFORE deploying since they are embedded at build time.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "project_id": {
      "type": "string",
      "description": "Project ID (UUID)"
    },
    "key": {
      "type": "string",
      "description": "Environment variable name (e.g., STRIPE_KEY, REDIS_URL, API_SECRET). Do NOT set DATABASE_URL — it is auto-managed"
    },
    "value": {
      "type": "string",
      "description": "Environment variable value. Will be encrypted at rest"
    }
  },
  "required": [
    "project_id",
    "key",
    "value"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-env(project_id)

List environment variables for a project. Values are masked for security. Auto-injected variables (DATABASE_URL, PGHOST, PGPORT, PGUSER, PGPASSWORD, PGDATABASE, PORT) may not appear in this list but are always available in the container at runtime.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "project_id": {
      "type": "string",
      "description": "Project ID (UUID)"
    }
  },
  "required": [
    "project_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🔴rollback(project_id)

Rollback a project to its previous deployment. This instantly swaps the container image without rebuilding — the previous image is reused for near-instant rollback. Uses the same blue-green strategy for zero downtime. The database is NOT rolled back (data persists across deployments). Use this when a deployment introduces bugs or breaks the app.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "project_id": {
      "type": "string",
      "description": "Project ID (UUID) to rollback. Use list-projects to find the ID"
    }
  },
  "required": [
    "project_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-status(project_id)

Get the current deployment status for a project, including the live URL (https://{slug}.sota.io), detected framework, and recent deployment history. Deployment statuses: pending (queued), building (build in progress), built (image ready), deploying (starting container + health checks), running (live and healthy), failed (build or health check error), stopped (replaced by newer deployment). Use this to verify a deployment succeeded after calling deploy.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "project_id": {
      "type": "string",
      "description": "Project ID (UUID) to check status for. Use list-projects to find the ID"
    }
  },
  "required": [
    "project_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡add-domain(project_id, domain)

Add a custom domain to a sota.io project. Each project supports up to 5 custom domains with automatic HTTPS via Let's Encrypt. Returns DNS setup instructions: for apex domains (example.com), add an A record pointing to 23.88.45.28; for subdomains (app.example.com), add a CNAME record pointing to {slug}.sota.io. Domain statuses: pending (waiting for DNS) → verified (SSL provisioning) → active (live with HTTPS). After DNS is configured, verification and SSL provisioning happen automatically.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "project_id": {
      "type": "string",
      "description": "Project ID (UUID) to add the domain to. Use list-projects to find the ID"
    },
    "domain": {
      "type": "string",
      "description": "Domain name to add (e.g. \"app.example.com\" or \"example.com\")"
    }
  },
  "required": [
    "project_id",
    "domain"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list-domains(project_id)

List all custom domains for a sota.io project. Shows domain name, status (pending/verified/active), and ID for each domain. Use get-domain with a domain ID to see DNS instructions and full details.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "project_id": {
      "type": "string",
      "description": "Project ID (UUID) to list domains for. Use list-projects to find the ID"
    }
  },
  "required": [
    "project_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-domain(project_id, domain_id)

Get details of a custom domain including its current status and DNS setup instructions. Domain statuses: pending (DNS not yet configured), verified (DNS confirmed, SSL provisioning), active (live with HTTPS). If status is 'pending', configure the DNS record as shown in the instructions.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "project_id": {
      "type": "string",
      "description": "Project ID (UUID). Use list-projects to find the ID"
    },
    "domain_id": {
      "type": "string",
      "description": "Domain ID (UUID). Use list-domains to find the ID"
    }
  },
  "required": [
    "project_id",
    "domain_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🔴remove-domain(project_id, domain_id)

Remove a custom domain from a sota.io project. This removes the domain mapping and its SSL certificate. The DNS records at your registrar are NOT automatically removed — clean those up manually. This action is immediate and irreversible.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "project_id": {
      "type": "string",
      "description": "Project ID (UUID). Use list-projects to find the ID"
    },
    "domain_id": {
      "type": "string",
      "description": "Domain ID (UUID). Use list-domains to find the ID"
    }
  },
  "required": [
    "project_id",
    "domain_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Prompts recomendados

retrieve_data
Get details about [item] from mcp
Herramientas esperadas: get-logs
fetch_info
Fetch [information type] using mcp
Herramientas esperadas: get-logs
list_items
List all [items] available in mcp
Herramientas esperadas: list-projects
browse_collection
Show me the [collection] from mcp
Herramientas esperadas: list-projects
explore_workflow
List available [items], then get details for each one using mcp
Herramientas esperadas: list-projectsget-logs

Comunidad

Califica este servidor

Evidencia

Observaciones recientes

verificadoversión no registrada14 herramientas
verificadoversión no registrada14 herramientas