de en es ja ko ru zh

Plesk

Name: Plesk
Author: FlayedOne

by FlayedOne

Overview Schema Source Related Servers Discussions Admin

Python

Remote

Servidor MCP de Plesk

Este servidor MCP para Plesk permite a los administradores gestionar sus servidores Plesk utilizando varios agentes y aplicaciones de IA. Se basa en la API REST de Plesk y la API REST de WP Toolkit, y proporciona capacidades de administración central, así como la capacidad de gestionar el servidor a través de comandos de shell y subir archivos al servidor.

El servidor MCP se ejecuta localmente en tu máquina, por lo que la información importante no sale de tu entorno.

Requisitos de Plesk

Se espera que el servidor MCP sea compatible con cualquier versión reciente de Plesk (no hay limitaciones estrictas) y cualquier sistema operativo (Linux o Windows) que Plesk soporte. Sin embargo, solo se ha probado en Plesk Obsidian 18.0.76, por lo que es preferible utilizar una versión de Plesk compatible.

Obviamente, el acceso a la API no debe estar deshabilitado en el servidor.

Related MCP server: cPanel MCP Server

Requisitos del servidor MCP

Necesitarás el gestor de paquetes de Python uv para ejecutar el servidor. Consulta la documentación oficial para obtener instrucciones de instalación.

Uso

Configura el servidor en tu mcp.json de VS Code o equivalente (en otros agentes o aplicaciones) usando una configuración como:

{
    "servers": {
        "plesk": {
            "command": "uvx",
            "args": [
                "plesk-mcp@latest"
            ],
            "env": {
                // Base URL of your Plesk server. May include port.
                // If you don't have a valid TLS certificate or want to use HTTP,
                // add the --insecure flag to the args above.
                // However, this is not recommended as you credentials may be leaked as a result.
                "PLESK_HOST": "https://plesk.example.net:8443",
                // API key (recommended).
                // Create via `plesk bin secret_key --create -description 'Plesk MCP'` on the server.
                "PLESK_API_KEY": "00000000-0000-0000-0000-000000000000",
                // Alternatively, you can use username and password.
                "PLESK_USERNAME": "admin",
                "PLESK_PASSWORD": "passwd"
            }
        }
    }
}

Es posible que desees utilizar un archivo de entorno (por ejemplo, mediante el parámetro "envFile") si tu agente o aplicación lo admite. Esto evitará poner las credenciales directamente en el archivo de configuración.

Consulta uvx plesk-mcp@latest --help para obtener detalles sobre las opciones disponibles y las variables de entorno.

Uso recomendado

Para un mejor comportamiento, se recomienda utilizar este servidor MCP en combinación con un servidor MCP de documentación. Selecciona plesk-local-docs-mcp o plesk-remote-docs-mcp. Esto permitirá al agente obtener información más precisa sobre el uso de Plesk cuando sea necesario.

Puedes adjuntar varios servidores Plesk a la vez si es necesario (por ejemplo, para gestionar múltiples servidores).

Aquí tienes un ejemplo de configuración:

{
    "servers": {
        "plesk-docs": {
            "command": "uvx",
            "args": [
                "plesk-local-docs-mcp@latest"
            ],
            "env": {
                "OPENAI_API_KEY": "sk-..."
            }
        },
        "plesk1": {
            "command": "uvx",
            "args": [
                "plesk-mcp@latest"
            ],
            "env": {
                "PLESK_HOST": "https://plesk1.example.net:8443",
                "PLESK_API_KEY": "00000000-0000-0000-0000-000000000000"
            }
        },
        "plesk2": {
            "command": "uvx",
            "args": [
                "plesk-mcp@latest"
            ],
            "env": {
                "PLESK_HOST": "https://plesk2.example.net",
                "PLESK_USERNAME": "admin",
                "PLESK_PASSWORD": "passwd"
            }
        }
    }
}

Desarrollo

Comando de ejecución del servidor MCP:

uv run plesk-mcp --log-level debug --insecure

Antes de confirmar (commit):

uv run ruff format
uv run ruff check --fix
uv run mypy .

Publicar:

uv build --clear
uv publish
mcp-publisher publish

Pruebas

Usando la imagen de Docker de Plesk

Si no tienes una instancia de Plesk pero quieres probar este servidor MCP, puedes usar la imagen de Docker de Plesk en su lugar:

docker run -d --rm --tmpfs /tmp --tmpfs /run --tmpfs /run/lock -v /sys/fs/cgroup:/sys/fs/cgroup --cgroupns host -p 80:80 -p 443:443 -p 8880:8880 -p 8443:8443 --name plesk plesk/plesk

El inicio de la imagen de Docker no es instantáneo, así que dale un minuto aproximadamente antes de intentar conectarte.

Y luego configura el servidor MCP como:

{
    "servers": {
        "plesk": {
            "command": "uvx",
            "args": [
                "plesk-mcp@latest",
                "--insecure"
            ],
            "env": {
                "PLESK_HOST": "https://localhost:8443",
                "PLESK_PASSWORD": "changeme1Q**"
            }
        }
    }
}

Sin servidor Plesk (Modo demo)

Alternativamente, ejecuta en modo demo desde las fuentes (con respuestas simuladas):

{
    "servers": {
        "plesk": {
            "command": "uv",
            "args": [
                "run",
                "plesk-mcp"
            ],
            "env": {
                "PLESK_HOST": "https://linux.demo.example.net",
                "PLESK_API_KEY": "-"
            }
        }
    }
}

Available Tools

6 tools

api_callA

Call Plesk API. Do not use any preconceived notions about how to use Plesk API. Instead validate usage with api_help tool.

ParametersJSON Schema

Name	Required	Description	Default
`name`	Yes	Name of the API to call. List available with api_list tool.
`params`	Yes	API call parameters. MUST check expected schema with api_help tool.

TDQS

A4.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It fails to disclose behavioral traits like whether it is read-only, error handling, or rate limits, only directing to api_help for parameter validation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core purpose, no waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's generic nature and lack of output schema, the description adequately directs to helper tools for details but lacks behavioral context and return value description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema already describes both parameters (name and params). The description adds value by directing to api_list for names and api_help for parameter schema, supplementing the schema coverage of 100%.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states its function: 'Call Plesk API.' It also warns against preconceived notions and directs to api_help, distinguishing it from sibling tools like api_help and api_list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells when to use (call Plesk API) and not to use preconceived notions, and instructs to validate with api_help tool, providing clear alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

api_helpA

Read-onlyIdempotent

Explain how to call a specific Plesk API.

ParametersJSON Schema

Name	Required	Description	Default
`name`	Yes	Name of the API to describe.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide readOnlyHint and idempotentHint. The description reinforces a read-only, idempotent operation (explain), and adds context about Plesk API. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that immediately conveys the tool's purpose with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple help tool with one parameter and an output schema, the description is mostly complete. It could mention what the explanation includes, but the output schema likely covers return structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the single parameter 'name'. The description adds context about 'Plesk API' but does not significantly extend beyond the schema's 'Name of the API to describe.' Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Explain how to call a specific Plesk API' clearly states the verb (Explain) and resource (specific Plesk API), and distinguishes it from siblings like api_call (which executes) or api_list (which lists APIs).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for obtaining help on calling an API, but does not explicitly contrast with when to use api_call, api_list, etc. No exclusions or alternatives are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

api_listB

Read-onlyIdempotent

List available Plesk APIs.

ParametersJSON Schema

Name	Required	Description	Default
`tags`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnly and idempotent. Description adds no additional behavioral detail (e.g., no mention of rate limits or data shape). This is acceptable given annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence is efficient and front-loaded. Could add relevant detail without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Simple list tool with output schema and annotations; missing description of tags parameter but otherwise complete for a basic operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and description does not explain the 'tags' parameter. The parameter is left ambiguous despite being optional.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action 'List available Plesk APIs' with a specific verb and resource. It is distinct from sibling tools like api_call (call API) and api_list_tags (list tags).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives (e.g., api_list_tags or api_call). Does not mention filtering or context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

api_list_tagsA

Read-onlyIdempotent

List available Plesk API tags. Start here to explore Plesk APIs.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.3/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint true. The description does not add further behavioral details beyond confirming a read-only list operation, which is consistent but not additional.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, 12 words. Every word serves a purpose, front-loading the function and usage hint. No redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, read-only tool with an output schema, the description is complete. It states what the tool does and its role as an entry point.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With zero parameters and 100% schema coverage, the baseline is 4. The description does not need to add parameter information, and it does not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'List available Plesk API tags' with the added directive 'Start here to explore Plesk APIs' clearly states the tool's function and distinguishes it from siblings like api_list (which likely lists APIs) and api_call.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'Start here to explore Plesk APIs' provides a clear context for when to use this tool, though it lacks explicit exclusions or alternatives. However, given the tool's simplicity, this is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

execA

Executes a command on the Plesk server and returns the result.

The command CWD is the home directory of the user (e.g. /root for root user, or /var/www/vhosts/example.com for a subscription user). This tool will reject long commands. Keep the total length of the command, stdin, and env vars under about 740 characters.

This tool will fail for subscriptions with no or chrooted shell access (chrootsh).

ParametersJSON Schema

Name	Required	Description
`command`	Yes	Command to execute. Don't use `bash` wrapper if it is not required for proper operation. NEVER use `bash -lc` for root context to avoid printing banner. ALWAYS use `bash -lc` when running in subscription context to ensure proper environment setup.
`subscription`	No
`stdin`	No
`env`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It discloses key behaviors: command execution, CWD, length limit, and failure for restricted shell access. However, it does not mention security implications, output format details, or timeout behavior, leaving some gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact, with two main sentences followed by targeted caveats. Every sentence adds specific, actionable information. It is well-structured and easy to scan, avoiding unnecessary verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema, the description does not need to detail return values. It covers essential execution context (CWD, length limits, failure cases) for a command execution tool. While more details on parameter interactions would help, the description is sufficiently complete for typical use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% (only 'command' has a detailed description). The description adds value by explaining CWD, length limits, and shell access constraints, but does not detail the 'subscription', 'stdin', or 'env' parameters. It partially compensates for the low schema coverage but not fully.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool executes a command on the Plesk server and returns the result, providing a specific verb and resource. However, it does not explicitly differentiate from sibling tools like api_call or upload, though the distinct function is obvious from context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides practical usage constraints such as CWD behavior (e.g., '/root' for root user), a character limit of ~740 characters, and failure conditions (no or chrooted shell access). It does not explicitly state when to use this tool versus alternatives, but the constraints themselves guide appropriate use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

uploadA

Uploads a file with the given content to the Plesk server and returns the file path.

The file will be uploaded to a temporary location returned by this tool and can be used in subsequent commands. The file is uploaded as 0600 psaadm:psaadm, so make sure to set proper permissions and ownership after moving it. For example, subscription files should typically have 0644 $user:psacln. Make sure to set both.

ParametersJSON Schema

Name	Required	Description	Default
`content`	Yes	Content of the file to upload.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses key behaviors: temporary location, ownership/permissions (0600 psaadm:psaadm), and need to set proper permissions after moving. It does not mention auth or rate limits, but the side effects are well covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise: three sentences front-loading the purpose, then providing usage and permission details without any wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, output schema exists), the description adequately covers what it does, where the file goes, and follow-up steps. It does not specify file size limits or overwrite behavior, but the core usage is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage for the single parameter 'content' with a clear description. The tool description adds no extra meaning beyond what is in the schema, earning a baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool uploads a file to the Plesk server and returns the file path. The verb 'uploads' and resource 'file' are specific, and the tool is distinct from siblings like api_call or exec.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides usage context: the file is uploaded to a temporary location and can be used in subsequent commands, with notes on permissions. However, it does not explicitly compare to alternatives or state when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

6 tool updatesv0.1.1May 3, 2026
- First observedapi_call
- First observedapi_help
- First observedapi_list
- First observedapi_list_tags
- First observedexec
- First observedupload

Deploy Server

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

A4/5.0

Scored 2026-05-03 18:55 across 6 tools

Disambiguation5/5

Each tool has a distinct purpose: API exploration (api_list, api_list_tags, api_help), API invocation (api_call), command execution (exec), and file upload (upload). No overlapping functionality.

Naming Consistency5/5

All tool names use lowercase with underscores where needed (api_call, api_list, api_list_tags, api_help, exec, upload). The pattern is predictable: API tools prefixed with 'api_', and standalone verbs for other actions.

Tool Count5/5

With 6 tools, the server covers essential operations for Plesk management: API discovery, API calls, shell commands, and file uploads. The count is well-scoped, not excessive or sparse.

Completeness4/5

The tool surface covers API interaction and server operations thoroughly. A minor gap is the lack of a download tool, but exec can be used to retrieve files, so agents can work around it.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

VeriTeknik AOAuth
com.veriteknik
Manage VeriTeknik servers, DNS, backups and support tickets from your AI assistant.
Networking & Infrastructure Cloud Platforms Customer Support
461
turbopress HostingOAuthDeprecated
de.turbopress
Manage turbopress hosting from Claude or ChatGPT: site health, domains, mail, SSL and AI Launch.
Cloud Platforms Networking & Infrastructure Monitoring
1
DilohostOAuth
es.dilohost
Hosting run by your AI agent: publish websites, apps, databases, domains and email from chat.
1
VozoraOAuth
io.vozora
Manage Vozora VPS servers, SSH keys, firewalls, DNS and usage from an AI agent.
1

Related MCP Servers

Plesk MCP Server
Cloud Platforms Security Monitoring
klan1
A
license
Not graded
quality
D
maintenance
Enables AI agents to manage Plesk hosting environments through a set of standardized tools for security, health monitoring, DNS, email, backups, and service management.
Updated 6 months ago (2026-04-28 21:43 UTC)
MIT
cPanel MCP Server
Cloud Platforms Databases File Systems
aandersen2323
A
license
A
quality
D
maintenance
A complete MCP server enabling AI assistants to manage cPanel hosting through natural language, including file, database, email, subdomain, and system operations.
Updated a year ago (2025-10-09 18:06 UTC)
16
1
MIT
whm-mcp-server
Networking & Infrastructure Security
hosthobbit
F
license
Not graded
quality
C
maintenance
Enables AI assistants to manage WHM hosting accounts and server administration tasks including account management, server stats, updates, SSL, backups, and email through a secure API.
Updated 21 days ago (2026-09-23 19:14 UTC)
11
-
cPanel MCP Server
Cloud Platforms Developer Tools File Systems
0xHayd3n
F
license
B
quality
C
maintenance
A comprehensive MCP server for managing cPanel hosting accounts through AI assistants. It supports DNS, email (DKIM/SPF), databases, domains, SSL, PHP, cron jobs, security, Git deployment, and more.
Updated a month ago (2026-09-10 10:47 UTC)
100
24
-