mcp-mediawiki-crunchtools
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEDIAWIKI_URL | Yes | Wiki base URL (e.g., https://en.wikipedia.org/w/) | |
| MEDIAWIKI_PASSWORD | No | Bot/user password | |
| MEDIAWIKI_USERNAME | No | Bot/user account for write operations | |
| MEDIAWIKI_HTTP_PASS | No | HTTP Basic Auth password | |
| MEDIAWIKI_HTTP_USER | No | HTTP Basic Auth username (.htaccess) |
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
} |
| 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_toolA | Full-text search across the wiki. Args: query: Search query string namespace: Namespace to search in (0=Main, default: 0) limit: Maximum results to return (default: 10, max: 50) Returns: Search results with titles, snippets, and metadata |
| get_page_toolB | Get page wikitext content by title. Args: title: Page title (e.g., "Main Page") Returns: Page content, revision info, and metadata |
| get_page_html_toolB | Parse a wiki page to HTML. Args: title: Page title to parse Returns: Parsed HTML content, categories, links, and sections |
| list_pages_toolA | List wiki pages with optional prefix filter. Args: prefix: Filter pages starting with this prefix namespace: Namespace to list (0=Main, default: 0) limit: Maximum results (default: 50, max: 500) from_title: Start listing from this title (for pagination) Returns: List of page titles with metadata |
| create_page_toolB | Create a new wiki page. Requires authentication. Args: title: Page title content: Page wikitext content summary: Edit summary (default: empty) Returns: Creation result with page info |
| edit_page_toolA | Edit an existing wiki page. Requires authentication. Args: title: Page title content: New page wikitext content summary: Edit summary (default: empty) minor: Mark as minor edit (default: False) Returns: Edit result with revision info |
| delete_page_toolA | Delete a wiki page. Requires admin authentication. Args: title: Page title to delete reason: Reason for deletion (default: empty) Returns: Deletion result |
| move_page_toolB | Move (rename) a wiki page. Requires authentication. Args: from_title: Current page title to_title: New page title reason: Reason for move (default: empty) move_talk: Also move the talk page (default: True) no_redirect: Do not create a redirect (default: False) Returns: Move result with old and new titles |
| list_categories_toolB | List all categories on the wiki. Args: prefix: Filter categories starting with this prefix limit: Maximum results (default: 50, max: 500) from_name: Start listing from this category (for pagination) Returns: List of category names with metadata |
| get_category_members_toolA | Get pages in a category. Args: category: Category name (with or without "Category:" prefix) member_type: Filter by type: page, subcat, file (default: all) limit: Maximum results (default: 50, max: 500) continue_from: Continue token for pagination Returns: List of category members with titles and types |
| get_page_categories_toolA | Get categories that a page belongs to. Args: title: Page title limit: Maximum categories to return (default: 50, max: 500) show_hidden: Include hidden categories (default: False) Returns: List of categories the page belongs to |
| list_recent_changes_toolA | List recent edits on the wiki. Args: namespace: Filter by namespace (default: all namespaces) limit: Maximum results (default: 50, max: 500) tag: Filter by tag name change_type: Filter by type: edit, new, log, categorize, external from_timestamp: Start from this timestamp (ISO 8601) Returns: List of recent changes with user, title, timestamp, and comment |
| parse_wikitext_toolA | Parse raw wikitext to HTML. Args: wikitext: Raw wikitext content to parse title: Context page title for template resolution (optional) Returns: Parsed HTML output |
| get_site_info_toolA | Get wiki configuration and version info. Returns: Site info including wiki name, version, base URL, and features |
| list_namespaces_toolA | List all namespaces on the wiki. Returns: List of namespaces with IDs, names, and canonical names |
| get_user_info_toolA | Get user details from the wiki. Args: username: Username to look up Returns: User details including edit count, registration date, and groups |
| list_user_contributions_toolA | List edits by a user. Args: username: Username whose contributions to list namespace: Filter by namespace (default: all) limit: Maximum results (default: 50, max: 500) from_timestamp: Start from this timestamp (ISO 8601) Returns: List of user contributions with titles, timestamps, and comments |
| get_file_info_toolA | Get file/image metadata from the wiki. Args: filename: File name (with or without "File:" prefix) Returns: File metadata including URL, size, dimensions, and MIME type |
| list_files_toolA | List files on the wiki. Args: prefix: Filter files starting with this prefix limit: Maximum results (default: 50, max: 500) mime_type: Filter by MIME type (e.g., "image/png") from_name: Start listing from this file (for pagination) Returns: List of files with metadata |
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 19 tools
The tool set cleanly separates page retrieval, HTML parsing, wikitext parsing, category traversal, user queries, file queries, and site metadata. Even similar-sounding page/HTML tools have clearly different inputs and outputs.
All 19 tools use snake_case with a uniform _tool suffix and mostly verb_noun construction (list_pages_tool, create_page_tool, get_user_info_tool). Minor deviation is search_tool, but it remains readable and consistent with the suffix convention.
At 19 tools, the server is slightly above the ideal 3–15 range but not excessive given MediaWiki's breadth; each tool maps to a meaningful read/write operation. It could be trimmed by folding some read variants, but it remains manageable.
The set covers page CRUD and move, search, categories, recent changes, users, files, namespaces, and site info. Minor gaps include page revision/history retrieval and file upload/delete, but core read/write workflows are well supported.