grokipedia-mcp-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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchB | Search Grokipedia full-text index. Args: query: Search terms. limit: Max results (1-50, default 10). offset: Pagination offset (default 0). |
| get_pageB | Fetch a Grokipedia page: title, summary, sections, citations, and URL. Tries the site's page-preview endpoint first, then falls back to parsing the public HTML page. Section text is capped (see "truncated"). |
| get_page_sectionA | Return one section by heading (exact case-insensitive match, else heading containing the text). Args: slug: Page slug, e.g. "Printed_circuit_board". heading: Section heading to find. include_subsections: If the section's own body is empty (a parent heading whose text lives in its subsections), return the subsections' text with their headings (default true). "subsections" always lists the nested headings. |
| get_page_citationsA | Return the citations / references for a page, with where each is cited. Each citation has "sections": the headings under which its inline marker appears in the article text (matched by exact URL; [] if never cited inline). When the article text has no usable inline markers (e.g. HTML fallback), "sections" is null and "section_mapping" is "unavailable"; mappings are never guessed. Args: slug: Page slug. include_context: Also return up to 3 short text snippets preceding each marker. |
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 4 tools
The tools mostly target distinct needs: search for discovery, get_page for full page retrieval, get_page_section for focused section content, and get_page_citations for reference details. However, get_page already includes sections and citations, so there is some overlap and an agent might occasionally wonder whether the specialized tools are needed.
Three tools follow a clear get_page_* pattern (get_page, get_page_section, get_page_citations), while search is a bare verb. This is a minor deviation from an otherwise predictable convention and remains readable.
Four tools is well-scoped for a read-only reference server: search plus full-page, section, and citation retrieval. Each tool has a clear role and none appear redundant enough to inflate the count.
The core read workflows for a wiki-like source are covered: discovery via search, full page content, section-level extraction, and citation/reference mapping. No obvious lifecycle gaps exist for this read-only domain.