Skip to main content
Glama

MediaWiki

mediawiki
Read-only

Get Wikipedia content directly: fetch articles by title, search full-text, and resolve footnotes and citations.

Instructions

Search and retrieve content from Wikipedia and other MediaWiki sites.

Use this for direct Wikipedia access without resorting to web_search with site: filters. Fetches articles by title (no URL guessing), runs native full-text wiki search, and resolves footnotes/inline citations on a specific article. Wikipedia URLs are also handled automatically by web_fetch_incisive.

Actions: page, search, references.

PARAMETER SPLIT: unlike other dedicated tools, this one uses two primary parameters:

  • title= for 'page' and 'references' (article identifier: title or URL)

  • query= for 'search' only (search terms) The dispatcher will reject mismatches with a specific error.

Query formats:

  • page: title (e.g. "Gödel's incompleteness theorems") or full Wikipedia URL. Supports section=, search= (within-page BM25), and slices= for targeted extraction.

  • search: keywords (e.g. "quantum entanglement"). Supports MediaWiki search operators.

  • references: title identifying the page; supply footnotes=[1,2] and/or citations=["#CITEREFFoo2005"] to resolve numbered footnotes and/or inline author-date citations. Both can be passed in one call.

search= operators (tantivy query language):

  • foo bar — match any term (whitespace is OR)

  • +foo +bar — require both terms

  • foo -bar — exclude 'bar'

  • "exact phrase" — adjacent words in order

  • "some words"~3 — phrase with up to 3-word gaps

  • (foo OR bar) baz — grouping + AND/OR/NOT

  • foo~ — fuzzy match (edit distance) Matching is case-insensitive; no stemming (search for both 'prompt' and 'prompts' if you want either). Stray punctuation in natural-language queries is silently dropped.

Wiki instance via wiki= parameter:

  • Language code: "en" (default), "de", "simple", "zh-yue", "pt-br"

  • Sister project: "commons", "wikidata", "meta", "species"

  • Hostname/URL: "en.wikipedia.org", "https://wiki.archlinux.org"

  • Ignored when title= is a full URL (URL wins)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
wikiNoWiki instance: language code ("en", "de", "simple", "zh-yue"), sister-project alias ("commons", "wikidata", "meta", "species"), hostname ("en.wikipedia.org"), or full URL ("https://wiki.archlinux.org"). Default "en" (English Wikipedia). Ignored when title= is a full URL.en
limitNoMaximum search results to return (default 10, max 50).
queryNoSearch terms — required for the 'search' action. Supports MediaWiki's native search operators.
titleNoPage identifier — article title (e.g. "Gödel's incompleteness theorems") or full URL. Required for 'page' and 'references' actions. When a full URL is supplied, the wiki= parameter is ignored.
actionYesThe operation to perform. page: fetch a Wikipedia/MediaWiki article by title or URL. search: native full-text search across articles. references: resolve numbered footnotes and/or inline author-date citations on a specific article.
offsetNoStarting position for search pagination.
searchNoWithin-page BM25 keyword search for the 'page' action — distinct from action='search' which does full-text wiki search across all articles.
slicesNoSlice index or list of indices to retrieve from a cached page (page action only).
sectionNoSection name or list of section names to extract (page action only). Matches heading text.
citationsNoInline author-date CITEREF key(s) to resolve for the 'references' action. Accepts '#CITEREFFoo2005', 'CITEREFFoo2005', or bare 'Foo2005'.
footnotesNoNumbered footnote(s) to retrieve for the 'references' action. Accepts an int or list of ints matching the [^N] markers in rendered page content.
namespaceNoMediaWiki namespace for search: 0=Article (default), 1=Talk, 4=Project (Wikipedia:), 14=Category, 100=Portal.
max_tokensNoLimit on content length in approximate token count (default 5000).
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint annotation, the description adds substantial behavioral detail: the dispatcher rejects mismatched parameters, search matching is case-insensitive with no stemming, punctuation is silently dropped, and the wiki parameter is ignored when a full URL is given. It also documents the tantivy query language behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-structured with clear sections (Actions, Query formats, search= operators, Wiki instance). Every section contributes essential information for correct invocation. It is appropriately detailed for a complex 13-parameter tool, though slightly verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema and 13 parameters, the description covers action-specific parameter requirements, error behavior, search query syntax, wiki instance selection, and within-page search semantics. It is sufficient for an agent to select the correct action and parameters without external clarification.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the schema has 100% description coverage, the description adds significant semantic value beyond the schema: it explains the parameter split (title vs query), specifies footnote/citation input formats, documents the search operator syntax, and clarifies how wiki aliases resolve. This goes well beyond the baseline for fully documented schemas.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Search and retrieve content from Wikipedia and other MediaWiki sites.' It enumerates three specific actions (page, search, references) and explicitly differentiates from alternatives like web_fetch_incisive by noting that Wikipedia URLs are handled automatically there, while this tool fetches by title.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance: 'Use this for direct Wikipedia access without resorting to web_search with site: filters.' It also mentions web_fetch_incisive as the alternative for URL handling, and clearly describes when to use page vs search vs references via the PARAMETER SPLIT section.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/blightbow/parkour-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server