Skip to main content
Glama

wikipedia-mcp-server

by io.github.cyanheads
OverviewDiscussionsAdmin

Get Wikipedia Summary

wikipedia_get_summary
Read-only

Fetch the short article summary that answers "what is X?". The extract is a truncated fragment from the start of the lead section — usually a sentence or two, and as little as a tenth of the lead — alongside the Wikidata QID (wikibase_item) for cross-referencing with wikidata-mcp-server, a short description, a thumbnail URL, the canonical article URL, the revision the extract was read from, and, for a geotagged article, latitude and longitude that pass straight to wikipedia_search_nearby to answer "what else is notable near this". For the lead section in full, call wikipedia_get_article with section_index 0. Redirect pages are followed automatically. When page_type is "disambiguation", the title matched a disambiguation page — call wikipedia_search_articles with a more specific query to find the intended article. Prefer this over wikipedia_get_article unless article depth is needed.

Input Schema

NameRequiredDescriptionDefault
titleYesArticle title (URL-decoded), e.g. "Python (programming language)". A trailing #fragment is accepted and ignored; the characters < > [ ] { } and | cannot appear in a Wikipedia page name.
languageNoWikipedia language edition code (default "en"). Examples: "fr", "de", "ja".en

Output Schema

NameRequiredDescriptionDefault
urlNoCanonical desktop URL of the article (e.g. "https://en.wikipedia.org/wiki/Eiffel_Tower"), for citing the page rather than composing a URL from the title.
errorNoPresent when the call failed. Absent on success.
titleNoResolved article title (may differ from input for redirects).
noticeNoGuidance when the existing page has no summary extract.
pageidNoWikipedia page ID. Absent when the API omits it.
extractNoPlain-text summary extract — a truncated fragment from the start of the lead section, not the whole lead. Superscripts and subscripts stay apart from the text beside them (10²³, H₂O), as wikipedia_get_article renders them. Call wikipedia_get_article with section_index 0 for the full lead.
languageNoLanguage edition queried.
latitudeNoWGS 84 latitude of the article subject in decimal degrees. Pass with longitude to wikipedia_search_nearby, whose inputs carry these names, to find other notable articles around the same point. Absent for an article that is not geotagged.
longitudeNoWGS 84 longitude of the article subject in decimal degrees. Pass with latitude to wikipedia_search_nearby, whose inputs carry these names, to find other notable articles around the same point. Absent for an article that is not geotagged.
page_typeNoPage type from the Wikipedia REST API. Common values: "standard" (regular article), "disambiguation" (disambiguation page), "no-extract" (article with no extract). When "disambiguation", call wikipedia_search_articles with a more specific query.
descriptionNoShort description of the article subject.
revision_idNoID of the revision the extract was read from. "https://<edition>.wikipedia.org/w/index.php?oldid=<revision_id>" is a permanent link to exactly that version.
last_modifiedNoISO 8601 timestamp of that revision, for dating the content.
thumbnail_urlNoURL of the article thumbnail image, if available.
wikibase_itemNoWikidata QID (e.g. "Q28865"). Use to chain into wikidata-mcp-server without a separate lookup.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / notice
      Added value: +{
+  "description": "Guidance when the existing page has no summary extract.",
+  "type": "string"
+}
  2. Changed1 schema field changed
    • changedOutput schema / properties / extract / description
      Previous value: -"Plain-text summary extract — a truncated fragment from the start of the lead section, not the whole lead. Call wikipedia_get_article with section_index 0 for the full lead."New value: +"Plain-text summary extract — a truncated fragment from the start of the lead section, not the whole lead. Superscripts and subscripts stay apart from the text beside them (10²³, H₂O), as wikipedia_get_article renders them. Call wikipedia_get_article with section_index 0 for the full lead."
  3. Changed5 schema fields changed
    • addedOutput schema / properties / last_modified
      Added value: +{
+  "description": "ISO 8601 timestamp of that revision, for dating the content.",
+  "type": "string"
+}
    • addedOutput schema / properties / latitude
      Added value: +{
+  "description": "WGS 84 latitude of the article subject in decimal degrees. Pass with longitude to wikipedia_search_nearby, whose inputs carry these names, to find other notable articles around the same point. Absent for an article that is not geotagged.",
+  "type": "number"
+}
    • addedOutput schema / properties / longitude
      Added value: +{
+  "description": "WGS 84 longitude of the article subject in decimal degrees. Pass with latitude to wikipedia_search_nearby, whose inputs carry these names, to find other notable articles around the same point. Absent for an article that is not geotagged.",
+  "type": "number"
+}
    • addedOutput schema / properties / revision_id
      Added value: +{
+  "description": "ID of the revision the extract was read from. \"https://<edition>.wikipedia.org/w/index.php?oldid=<revision_id>\" is a permanent link to exactly that version.",
+  "type": "string"
+}
    • addedOutput schema / properties / url
      Added value: +{
+  "description": "Canonical desktop URL of the article (e.g. \"https://en.wikipedia.org/wiki/Eiffel_Tower\"), for citing the page rather than composing a URL from the title.",
+  "type": "string"
+}
  4. Changed4 schema fields changed
    • changedInput schema / properties / title / description
      Previous value: -"Article title (URL-decoded), e.g. \"Python (programming language)\"."New value: +"Article title (URL-decoded), e.g. \"Python (programming language)\". A trailing #fragment is accepted and ignored; the characters < > [ ] { } and | cannot appear in a Wikipedia page name."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `not_found`: No Wikipedia article exists for the given title. `invalid_language`: The language is not a valid BCP 47 code, or names a Wikipedia edition that does not exist. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `not_found`: No Wikipedia article exists for the given title. `invalid_title`: The title contains characters MediaWiki cannot name a page with. `invalid_language`: The language is not a valid BCP 47 code, or names a Wikipedia edition that does not exist. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
-  "not_found",
-  "invalid_language"
-]New value: +[
+  "not_found",
+  "invalid_title",
+  "invalid_language"
+]
    • changedOutput schema / properties / extract / description
      Previous value: -"Plain-text lead-section extract."New value: +"Plain-text summary extract — a truncated fragment from the start of the lead section, not the whole lead. Call wikipedia_get_article with section_index 0 for the full lead."
  5. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the rest — and it does: automatic redirect following, the non-obvious truncation behavior (a tenth of the lead is far less than most agents would assume), the disambiguation signal, and the geotag passthrough to wikipedia_search_nearby. These are behavioral traits an agent could not infer from structured fields.

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 purpose and the alternative routing are front-loaded and the sentences are dense with useful content. However, the long catalogue of return fields (QID, short description, thumbnail, canonical URL, revision, lat/long) is partly redundant since an output schema exists, and it slows the read before the decision-relevant routing rules arrive.

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

Completeness4/5

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

For a two-parameter read tool with full schema coverage, an output schema, and minimal annotations, this covers nearly everything: scope, truncation, redirects, disambiguation handling, and sibling routing. The one gap is what happens when the title doesn't resolve to any page — no error or not-found behavior is described.

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

Parameters3/5

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

Schema coverage is 100% and both parameters are fully documented in the schema, so the baseline is 3. The description adds only an implicit gloss on title being the "X" in "what is X?" — it says nothing about the language parameter's effect on the returned extract or the QID.

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?

It names a specific verb and resource (fetch the short article summary), defines the scope of what a 'summary' means here (truncated fragment of the lead, sometimes as little as a tenth), and explicitly contrasts itself with wikipedia_get_article. An agent can distinguish it from every sibling without opening a schema.

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?

It states the positive case ("what is X?" lookups), the explicit alternative for depth (wikipedia_get_article with section_index 0), a routing rule when page_type is disambiguation (retry with wikipedia_search_articles), and a general preference over get_article. When-to-use and when-not-to-use are both covered.

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

All wikipedia-mcp-server toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources