plesk-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PLESK_API_KEY | No | Plesk API key referenced as env:PLESK_API_KEY in the example configuration for apiKey authentication. | |
| PLESK_MCP_ACCESS | No | Controls server-side confirmation for write tools. Valid values: confirm (default), full, client, off, none, write. Invalid values fall back to confirm and log a warning. | confirm |
| PLESK_DB_PASSWORD | No | MySQL password referenced as env:PLESK_DB_PASSWORD in the example configuration. | |
| PLESK_PROJECT_ROOT | No | Path to the project that contains .plesk/config.json. Use when the MCP client does not support setting cwd. | |
| PLESK_GLOBAL_CONFIG | No | Path to a different global configuration file instead of ~/.config/plesk-mcp/config.json. | |
| MYSQL_LOCAL_1_PASSWORD | No | Password referenced as env:MYSQL_LOCAL_1_PASSWORD in the localDatabases example. | |
| PLESK_CLIENT_A_PASSWORD | No | Password referenced as env:PLESK_CLIENT_A_PASSWORD in the basic authentication example for client-a. | |
| PLESK_CLIENT_A_DB_PASSWORD | No | MySQL password referenced as env:PLESK_CLIENT_A_DB_PASSWORD in the example configuration for client-a. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| servers_listC | No configuration is loaded. Returns the configuration error. |
| project_infoC | No configuration is loaded. Returns the configuration error. |
| doctorC | No configuration is loaded. Returns the configuration error. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
The three names hint at different intents (listing servers, project metadata, diagnostics), but every description is the identical 'No configuration is loaded. Returns the configuration error.', giving an agent no way to know what each tool actually returns or when to prefer one over another. `project_info` in particular is ambiguous in a Plesk context (which project? which info?).
`servers_list` uses a noun_plural + verb suffix, `project_info` is noun + attribute, and `doctor` is a bare noun with no resource qualifier. Three tools, three different conventions, with no shared verb_noun pattern to predict new tools from.
Three tools is borderline thin: a Plesk management server would need domain, mail, database, and subscription operations, and these three read more like bootstrap/diagnostic utilities than a scoped surface. The count itself isn't extreme, but it feels undersized for the apparent domain.
The implied domain is Plesk hosting administration, yet the surface offers no create/update/delete or even read operations for domains, websites, mailboxes, or databases — only a health check, a server list, and an info call. There are significant gaps that would block any real management workflow.