Skip to content

wikipedia-mcp-server

io.github.cyanheads/wikipedia-mcp-servercyanheadsstreamable-httpv0.3.1Scanned

Search and read Wikipedia articles and sections, list cited references, nearby pages, and languages.

7 tools: 7 only read.

Tools: 0 delete, 0 irreversible, 0 write, 7 read.
  • Reads private data · 3
  • Reads text others write · 7
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the wikipedia-mcp-server can do

The wikipedia-mcp-server is published by the GitHub account cyanheads. It has 7 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

3 tools read private data (wikipedia_get_article, wikipedia_get_sections and wikipedia_get_references); 7 tools bring in text other people can write (wikipedia_search_articles, wikipedia_get_summary, wikipedia_get_article and 4 more).

The fixed checks matched 1 finding (long-description). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 4 times since Anlyon Radar first saw them.

Last scanned Nov 11, 2026, version 0.3.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

7 tools

Only reads 7Show 7 read-only tools
  • wikipedia_get_articleFetch article content as clean plain text.Reads private dataReads text others write1 finding

    Why it is in this group

    • The name "wikipedia_get_article" says "get": a word for reading.

    What it can reach

    • private-dataThe input names a table (input.table_index), and the tool reads: it reads databases.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description is 2,499 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...ages are followed automatically, and the citation fields name the target article."

      What this check looks for
    Description, as the server wrote it
    Fetch article content as clean plain text. Without section_index: returns the full article with == Section == markers preserved for structure — or, when the article exceeds the size budget, a compact section outline (truncated: true) that points to wikipedia_get_sections plus a section_index read instead of the full text. With section_index (from wikipedia_get_sections): returns that section and every subsection nested under it, each heading above its own body. section_index 0 is the lead section, the text above the first heading, which is the full prose wikipedia_get_summary returns only a truncated fragment of. Section-targeted reads are faster and smaller when only part of the article is needed. Both paths keep superscripts and subscripts apart from the text beside them (10²³, H₂O), render formulas as their TeX, render code samples as fenced blocks with their indentation intact, and render list items as "- " or numbered "N." lines indented two spaces per nesting level, the indent capped at 16 levels. A section read also renders data tables as pipe-delimited rows (header row first) and infoboxes as "label: value" lines; a table too large to include leaves a "[table omitted: N rows (table T)]" marker. Pass table_index: T with section_index to read only that table in complete row pages whose table text fits within 40,000 UTF-8 bytes on both surfaces. Follow next_cursor as cursor with the same inputs to continue at the pinned revision; caption/header/delimiter appear once. An indivisible oversized row or first-page caption/header is returned alone with oversized_row: true. The full-article path carries no data tables or infoboxes, so read the section for those. Phylogenetic clade trees render as fenced, indented branches, with unnamed forks preserved; unparseable trees leave "[table omitted: unparseable clade]". Clade trees have no table_index. In a section read, tables used only for layout, such as multi-column lists, keep their content as ordinary text; the full-article path drops them, so read the section for those lists. Page furniture is omitted as well — maintenance banners, sister-project and library-resource boxes, portal bars, and spoken-article notices — while a hatnote naming a related article is kept. Every read returns the canonical article URL and the ID of the revision it was read from, for citation; a full read also returns that revision's timestamp. Redirect pages are followed automatically, and the citation fields name the target article.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • wikipedia_get_languagesList the language editions available for a Wikipedia article.Reads text others writeNo findings

    Why it is in this group

    • The name "wikipedia_get_languages" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    List the language editions available for a Wikipedia article. Returns language codes, article titles in each language, and full URLs. Useful for cross-language research and for discovering the correct article title in a target language before fetching it. A popular article exists in hundreds of editions, so pass editions to narrow the answer to the codes you care about — the codes with no article come back under missing, and total_languages still reports the full count. Redirect pages are followed automatically, and source_title reports the resolved article the links belong to. The language parameter specifies which edition to query from.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • wikipedia_get_referencesList the footnotes an article cites — its reference lists, in document order — with each footnote's text, external links (archive copies included), and DOIs.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "wikipedia_get_references" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "list" and "document": it reads documents.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    List the footnotes an article cites — its reference lists, in document order — with each footnote's text, external links (archive copies included), and DOIs. wikipedia_get_article drops footnote markers and reference lists, so use this for the sources behind a claim. label is the in-text marker without brackets; group names a notes list such as "lower-alpha" and is absent for the main list. A short citation such as "Galinsky 2012, pp. 75–76" carries work_ids, and works on the same page holds the full citations they name, each once. Pages hold whole footnotes within 40,000 UTF-8 bytes on both surfaces; follow next_cursor as cursor with the same title and language to continue at the same revision. Bibliography and further-reading entries no footnote points to are not listed — read those sections with wikipedia_get_article. Redirects are followed; the revision_id and url cite the article read.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • wikipedia_get_sectionsFetch the table of contents for a Wikipedia article.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "wikipedia_get_sections" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "fetch" and "table": it reads databases.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Fetch the table of contents for a Wikipedia article. Returns section titles, heading levels, section numbering (e.g. "2.1"), and section_index values. The first entry is the lead section, index 0, titled Introduction — the text above the first heading, which Wikipedia's own table of contents omits. Pass a section_index to wikipedia_get_article to retrieve just that section. Useful for enumerating article structure before doing a targeted section read. Redirect pages are followed automatically.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • wikipedia_get_summaryFetch the short article summary that answers "what is X?".Reads text others writeNo findings

    Why it is in this group

    • The name "wikipedia_get_summary" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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. Redirects are followed and reported in redirected_from, and in redirect_section when the alias points into a section; the extract still covers the whole article. 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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • wikipedia_search_articlesSearch Wikipedia articles by full-text query.Reads text others writeNo findings

    Why it is in this group

    • The name "wikipedia_search_articles" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Search Wikipedia articles by full-text query. Returns ranked results with plain-text titles, short descriptions, Wikidata QIDs, snippets (HTML stripped), page IDs, and word counts — the description is usually enough to tell same-named articles apart without a summary call per result. When Wikipedia has a spelling correction for the query, it is returned as suggestion. Best when the exact article title is unknown or when multiple articles on a topic are needed. Pass a result title to wikipedia_get_summary, wikipedia_get_article, or wikipedia_get_sections for follow-up reads. Use offset to page beyond the first result page. Supports all Wikipedia language editions.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • wikipedia_search_nearbyFind Wikipedia articles about places near a geographic coordinate.Reads text others writeNo findings

    Why it is in this group

    • The name "wikipedia_search_nearby" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Find Wikipedia articles about places near a geographic coordinate. Returns articles sorted by distance from the query point, with titles, short descriptions, Wikidata QIDs, page IDs, coordinates, and distance in meters. Useful for "what is notable near X?" research workflows. Only articles carrying their own coordinate tag (GeoData, set on the article itself — not the Wikidata item's coordinate) are returned, and that tag is what places and measures each result; not all articles about locations are geotagged, and an article whose tag is wrong appears where the tag puts it, which its description usually makes plain.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data3
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write7
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:35 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
0
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

Findings

Matches of fixed checks, with the text they matched.

1 info
  • The description is 2,499 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...ages are followed automatically, and the citation fields name the target article."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools7 changed.~7 changedView diff
  2. Tools1 added, 1 changed.+1 added~1 changedView diff
  3. Tools1 changed.~1 changedView diff
  4. Tools2 changed.~2 changedView diff

Install

Pinned to version 0.3.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http wikipedia https://wikipedia.caseyjhand.com/mcp
claude mcp add --transport http wikipedia https://wikipedia.caseyjhand.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__wikipedia__wikipedia_search_articles",
      "mcp__wikipedia__wikipedia_get_summary",
      "mcp__wikipedia__wikipedia_get_article",
      "mcp__wikipedia__wikipedia_get_sections",
      "mcp__wikipedia__wikipedia_search_nearby",
      "mcp__wikipedia__wikipedia_get_languages",
      "mcp__wikipedia__wikipedia_get_references"
    ],
    "ask": [],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as wikipedia. Review it before you use it.

Capability tags behind 7 rules
  • mcp__wikipedia__wikipedia_search_articles untrusted-input
  • mcp__wikipedia__wikipedia_get_summary untrusted-input
  • mcp__wikipedia__wikipedia_get_article private-data, untrusted-input
  • mcp__wikipedia__wikipedia_get_sections private-data, untrusted-input
  • mcp__wikipedia__wikipedia_search_nearby untrusted-input
  • mcp__wikipedia__wikipedia_get_languages untrusted-input
  • mcp__wikipedia__wikipedia_get_references private-data, untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.cyanheads/wikipedia-mcp-server/verify?hash=1b8a8cd7b45cbf1a285a97b3a69e08e99d3c09ae914d8353c2f05e2d9f1f015c" | jq -e '.changed == false'

Pinned hash 1b8a8cd7b45c, from Nov 11, 2026, 17:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.cyanheads/wikipedia-mcp-server/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.cyanheads/wikipedia-mcp-server
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.cyanheads/wikipedia-mcp-server.svg)](https://radar.anlyon.com/servers/io.github.cyanheads/wikipedia-mcp-server)

Source: MCP Registry · repository. Synced Nov 11, 2026, 17:17 UTC.

wikipedia-mcp-server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the wikipedia-mcp-server safe?

No scan can promise that. What its definitions show: 7 tools, all of which only read, and 1 finding from fixed checks. Read-only tools can still pass private data to a model.

Can the wikipedia-mcp-server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the wikipedia-mcp-server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the wikipedia-mcp-server have?

7 tools: 7 read. wikipedia_search_articles, wikipedia_get_summary, wikipedia_get_article, wikipedia_get_sections, wikipedia_search_nearby, wikipedia_get_languages and wikipedia_get_references.

Does the wikipedia-mcp-server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the wikipedia-mcp-server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the wikipedia-mcp-server changed its tools?

Yes, 4 times since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.