mst-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_documentsA | Lists the filenames of all available documentation files in the server. |
| read_documentA | Reads and returns the contents of a specific documentation file. Args: filename: The exact name of the file to read (e.g., 'SDK.txt'). |
| search_documentsB | Searches for a keyword or query inside all documents and returns matching lines with line numbers. Args: query: The search term or keyword to find. |
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
Each tool targets a distinct operation: listing filenames, reading a specific file, and searching content. There is no overlap in functionality.
All tools follow a consistent verb_noun pattern (list_documents, read_document, search_documents), making the naming predictable and easy to understand.
With only 3 tools, the server is minimal but well-scoped for its purpose of documentation access. While it could potentially include a tool for metadata, the current count is reasonable.
The server covers the core operations of listing, reading, and searching documentation files. Minor gaps like document metadata retrieval are not essential for basic usage, so the surface feels complete.