MCP Spark Documentation Server
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": 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_documentationA | Search Apache Spark documentation by keyword query. Args: query: Search terms to find in the documentation. Supports full-text search with stemming (e.g., "stream" matches "streaming", "streams"). section: Optional section to filter results. Common sections include: 'sql-ref', 'api', 'streaming', 'mllib', 'graphx', 'structured-streaming', etc. limit: Maximum number of results to return (default: 10, max: 50). Returns: JSON-formatted search results with title, URL, snippet, and relevance score. |
| read_documentationA | Read the full content of a specific Spark documentation page. Args: path: The relative path to the documentation file (e.g., 'sql-ref/sql-syntax.md' or 'api/python/index.md'). This path is returned in search results. Returns: The full markdown content of the documentation page, or an error message if the page is not found. |
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 2 tools
Search and read are completely distinct operations with no overlap. Search finds relevant pages, read retrieves content, and each has clearly defined inputs.
Both tools follow the consistent verb_noun pattern (search_documentation, read_documentation) with snake_case, making the API predictable and clean.
Two tools is borderline for a minimal server, but for a documentation-specific purpose, search and read are the essential operations. It feels slightly thin but not unreasonable.
The tool surface covers core documentation workflows: discovering relevant pages and reading their content. Minor gaps like listing all sections or navigating a table of contents exist, but they are non-blocking.