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": 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 |
|---|---|
| searchA | Search for articles in Grokipedia with optional filtering and sorting. |
| get_pageA | Get complete page information including metadata, content preview, and citations summary. |
| get_page_contentA | Get only the article content without citations or metadata. |
| get_page_citationsA | Get the citations list for a specific page. |
| get_linked_pagesA | Get pages that are linked from the specified article. Grokipedia no longer publishes a curated linked-pages field, so links are derived from /page/ markdown links in the article content and ranked by mention frequency, then first position. |
| get_page_sectionC | Extract a specific section from an article by header name. |
| get_page_sectionsA | Get a list of all section headers in an article. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| research_topic | Research a topic by searching and retrieving detailed information |
| find_sources | Find authoritative sources and citations for a topic |
| explore_related | Explore topics related to a specific article |
| compare_topics | Compare two topics side by side |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Most tools are clearly distinct: search finds articles, get_page retrieves metadata, get_page_content isolates body text, get_page_citations returns references, and get_page_sections lists headers. However, get_page and get_page_content could be confused since both return article content, though the descriptions clarify that get_page includes metadata and citations while get_page_content is content-only.
Tool names mostly follow a consistent verb_noun pattern: get_page, get_page_content, get_page_citations, get_page_sections, get_linked_pages, search. The only deviation is 'search' lacking a noun (e.g., search_pages), but it is still readable and predictable.
Seven tools is well-scoped for a wiki/knowledge-base server. Each tool covers a distinct retrieval need: search, page metadata, content, citations, sections, section detail, and linked pages. No redundant or unnecessary tools.
The server covers the main read-only retrieval workflows for a wiki: search, get page, get content, get citations, get sections, and get linked pages. Minor gaps include no way to get a page's full raw markdown in one call (content preview only) and no direct page history or related-pages API, but agents can work around these with existing tools.