mcp-plesk-dev-docs
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENROUTER_API_KEY | No | API key for OpenRouter (required for AI-synthesized answers) | |
| PLESK_MODEL_PROFILE | No | Model profile: light, medium, or full-tq | light |
| PLESK_ENABLE_SAMPLING | No | Enable AI-synthesized answers | true |
| PLESK_INDEX_SUMMARIES | No | Enable file-level summaries | true |
| PLESK_DAEMON_AUTO_WARMUP | No | Preload models on startup | true |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_mcp_plesk_dev_docsC | Search the unified Plesk documentation for a specific query. |
| get_file_contentA | Retrieve the full content of a specific documentation file. Use this when you have a filename from a search result and need more context than what was provided in the search snippets. |
| resolve_referencesA | Find other files that reference a specific symbol or topic. Useful for finding usage examples of a class, method, or CLI command across the documentation. |
| warmup_serverA | Preload the active profile models and table without running indexing. |
| daemon_healthB | Return daemon-centric readiness status. |
| list_model_profilesA | List built-in model profiles and show the active profile. |
| refresh_knowledgeA | Index Plesk documentation into LanceDB. This tool provides a blocking refresh that returns a report of the
indexing operation. For very large documentation sets, use
|
| trigger_index_syncC | Trigger a background indexing job for Plesk documentation. Returns a job_id that can be used with |
| check_sync_statusB | Check the status of a background indexing job. |
| requantize_knowledgeB | Rebuild the TurboQuant index from stored vectors. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| plesk-extension-dev-guide | Generate a starter guide for developing a new Plesk extension. |
| plesk-api-integration | Instructions and examples for integrating with a Plesk API operation. |
| plesk-cli-reference | Get detailed reference information for a Plesk CLI command. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Each tool has a clearly distinct purpose. Search, file retrieval, reference resolution, indexing operations, system health, and profile management are all separate concerns with no overlapping functionality.
Most tools follow a verb_noun pattern (e.g., get_file_content, trigger_index_sync), but 'search_mcp_plesk_dev_docs' includes the server name, and 'daemon_health' is noun_noun. These minor deviations from the dominant pattern prevent a perfect score.
With 10 tools, the set is well-scoped for a documentation server that includes indexing, search, and system health. Each tool serves a clear function without unnecessary bloat or sparseness.
The tool set covers the core lifecycle: indexing (refresh, trigger, check), search, retrieval, reference resolution, and system management. Minor gaps exist, such as the lack of a tool to list documentation sections or metadata, but these are not critical.