Skip to content

wikidata-mcp-server

io.github.cyanheads/wikidata-mcp-servercyanheadsstreamable-httpv0.4.1Scanned

Search and fetch Wikidata entities, execute SPARQL queries, and resolve external identifiers.

7 tools: 1 change things and 6 only read.

Tools: 0 delete, 0 irreversible, 1 write, 6 read.
  • Reads private data · 1
  • Reads text others write · 7
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • 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 wikidata-mcp-server can do

The wikidata-mcp-server is published by the GitHub account cyanheads. It has 7 tools. It can create or change data (1 tool: wikidata_sparql_query), but cannot delete data. 6 tools only read.

1 tool reads private data (wikidata_resolve_external_id); 7 tools bring in text other people can write (wikidata_search_entities, wikidata_get_entity, wikidata_get_labels and 4 more).

The fixed checks matched 2 findings (annotation-conflict and long-description). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.

Last scanned Nov 22, 2026, version 0.4.1.

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

Changes things 1Claude Code: ask
  • wikidata_sparql_queryExecute a SPARQL SELECT query against the Wikidata Query Service.Reads text others write1 finding

    Why it is in this group

    • The name "wikidata_sparql_query" says "query": a word for reading.
    • The description's first verb is "execute": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "wikidata_sparql_query" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "wikidata_sparql_query" says "query": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Execute a SPARQL SELECT query against the Wikidata Query Service. Full graph power: multi-hop traversals, aggregations, subqueries, OPTIONAL, FILTER, UNION, BIND. Standard Wikidata prefixes (wd:, wdt:, p:, ps:, pq:, wikibase:, bd:, rdfs:, schema:) are auto-injected. The wikibase:label SERVICE is also auto-injected when the query references a ?<var>Label, ?<var>Description, or ?<var>AltLabel variable and declares no label SERVICE of its own — so you can use ?itemLabel without writing the boilerplate. Scholarly articles, and every triple they own (DOI, PMID, authorship), live in a separate graph reachable only inside SERVICE wdsubgraph:scholarly_articles { … } (wdsubgraph: is predeclared). The injected label SERVICE runs on the main graph, so read a scholarly article's label inside that block, with BIND(?paperLabel AS ?paperLabel) and a label SERVICE there; a query that writes a label SERVICE gets none injected, so add a top-level one for main-graph labels. Hard server timeout is 60s; use LIMIT to keep queries fast. Each call returns at most 4,000 rows; a larger result returns its first rows with truncated, shown, and cap in place of totalCount — narrow the WHERE clause or aggregate in the query, or, for a result not much larger than that, page with ORDER BY plus LIMIT and OFFSET. Bindings use the SPARQL 1.1 JSON format: each value is { type, value, "xml:lang"?, datatype? }. Use wikidata_get_labels to humanize QID results from this tool.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
Only reads 6Show 6 read-only tools
  • wikidata_get_entityFetch a Wikidata entity (item or property) by QID or PID.Reads text others writeNo findings

    Why it is in this group

    • The name "wikidata_get_entity" 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 a Wikidata entity (item or property) by QID or PID. The fields parameter narrows the upstream fetch, not just the response — asking for labels alone costs a fraction of the whole entity, so name the fields you need. Omit fields for all data; a well-connected item is large enough to overflow, and an oversized entity returns kind: "outline" — the field categories with their byte sizes — instead of the data. Follow its retrieval_notice literally rather than picking from sections yourself — it names a fields set already measured to fit, since category sizes are additive and requesting them all would overflow again; for a category too large to deliver whole (statements or sitelinks on a major item) it names the sibling tool that can narrow it. Q-IDs (e.g. Q76) fetch items; P-IDs (e.g. P31) fetch properties from the correct endpoint automatically. Use wikidata_get_statements for deep claim traversal with label resolution, and whenever an entity's statements are large — its properties parameter selects individual P-IDs, granularity fields does not carry.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • wikidata_get_labelsResolve QIDs or PIDs to their human-readable labels and descriptions, with no claim data.Reads text others writeNo findings

    Why it is in this group

    • The name "wikidata_get_labels" 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
    Resolve QIDs or PIDs to their human-readable labels and descriptions, with no claim data. Resolves up to 500 distinct IDs per call, batched automatically; distinct IDs past the first 500 come back in deferredIds to send in a follow-up call. Accepts bare IDs (Q76), entity URIs (http://www.wikidata.org/entity/Q76), and wd:Q76 — the forms wikidata_sparql_query returns — so its results can be humanized as they are.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • wikidata_get_statementsFetch property claims for a Wikidata entity with qualifier and reference detail.Reads text others writeNo findings

    Why it is in this group

    • The name "wikidata_get_statements" 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 property claims for a Wikidata entity with qualifier and reference detail. Item QIDs and quantity units — in values, qualifiers, and references — are resolved to human-readable labels by default, and every P-ID the statements name comes back labelled in propertyLabels. Each property returns up to limit statements (default 10) starting at offset, in upstream order; propertyTotals counts every statement each property holds, and nextOffset, present while any property holds more, continues every property at once. Use the properties parameter to fetch only specific P-IDs — omitting it returns every property, and a well-connected item (a country, a major city) carries hundreds of them: more than fits inline. A page of several properties over 24,000 bytes before labels comes back as kind: "outline" — every P-ID on the page with its byte size, largest first — instead of the statements; re-call with the same id, limit, offset, and rank plus properties:[...] naming P-IDs whose sizes sum to 24,000 or less (the retrieval_notice names one such set). Labels are added after that check, so a returned page can run past 24,000 bytes by their size, and a single property is never outlined: it returns its window whatever the size. Designed for fact verification: "what does Wikidata say about this entity's {property}?". For a current value, rank: "best" keeps each property's preferred statements, or its normal ones when none is preferred, and never deprecated ones — the statements SPARQL's wdt: reads. Check qualifiers and references for temporal scope and evidence.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: true
  • wikidata_resolve_external_idLook up a Wikidata entity by an external identifier such as a DOI, PubMed ID, ORCID iD, OpenAlex ID, or IMDb ID.Reads private dataReads text others write1 finding

    Why it is in this group

    • The name "wikidata_resolve_external_id" says "resolve": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "db": it reads databases.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description is 2,116 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...either case, so it is tried as given and then with that letter in the other case."

      What this check looks for
    Description, as the server wrote it
    Look up a Wikidata entity by an external identifier such as a DOI, PubMed ID, ORCID iD, OpenAlex ID, or IMDb ID. Returns match=<entity> on success, match=null when not found, and match=null with multipleMatches populated when a Wikidata data integrity issue causes more than one entity to claim the same external ID. The identifier matches through statements of every rank — entities holding it at best rank first, then at another non-deprecated rank, then deprecated — and each match reports the rank of the statement it was found through. The lookup searches both the main Wikidata graph and the scholarly-article graph, where scholarly articles and the DOIs and PubMed IDs on them live; when one does not answer, the result covers the other, with unavailableGraphs naming the one missed. Common cross-server join use cases: CrossRef DOI → Wikidata paper QID (P356), PubMed PMID → Wikidata paper QID (P698), ORCID → author QID (P496), OpenAlex ID → entity QID (P10283). The property must be one whose Wikidata data type is external-id — item-valued or media properties (e.g. P31 instance-of, P18 image) are rejected rather than returning an empty match. Known value forms are normalized automatically. Surrounding whitespace is trimmed. Resolver prefixes are stripped, in any case and with https://, http://, or no scheme: doi.org/, dx.doi.org/, www.doi.org/, and doi: for DOIs; pubmed.ncbi.nlm.nih.gov/, www.ncbi.nlm.nih.gov/pubmed/, and PMID: for PubMed IDs; orcid.org/, www.orcid.org/, and orcid: for ORCID iDs; openalex.org/ and api.openalex.org/ with an optional entity path for OpenAlex IDs; and the title, name, company, and event pages of imdb.com, www.imdb.com, and m.imdb.com for IMDb IDs; ror.org/ for ROR; and arxiv.org/abs/ or arXiv: for arXiv. PMC is stripped from numeric PMCIDs, and ISNI values displayed in four space-separated groups are compacted. DOIs are uppercased, ORCID iDs regrouped with hyphens and an uppercase X check character, and IMDb IDs lowercased. An OpenAlex ID is stored with its entity letter in either case, so it is tried as given and then with that letter in the other case.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • wikidata_search_entitiesSearch Wikidata for items or properties by text query.Reads text others writeNo findings

    Why it is in this group

    • The name "wikidata_search_entities" 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 Wikidata for items or properties by text query. Returns QIDs or PIDs with labels, descriptions, and match metadata indicating whether the hit was on a label or alias. Use type="item" for real-world concepts (people, places, works) and type="property" to find predicate P-IDs. The endpoint returns no total count: page by sending each page's nextOffset as offset until a page returns no results or no nextOffset. Only the first 10,000 results are reachable.

    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 data1
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
1
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
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://wikidata.caseyjhand.com/mcp: tools/list returned 7 tools to an anonymous client, including wikidata_sparql_query (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn1 info
  • The server marks "wikidata_sparql_query" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "wikidata_sparql_query" says "query": a word for reading.

    What this check looks for
  • The description is 2,116 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...either case, so it is tried as given and then with that letter in the other case."

    What this check looks for

History

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

  1. Tools2 changed.~2 changedView diff
  2. Tools7 changed.~7 changedView diff
  3. Tools1 changed.~1 changedView diff

Install

Pinned to version 0.4.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http wikidata https://wikidata.caseyjhand.com/mcp
claude mcp add --transport http wikidata https://wikidata.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__wikidata__wikidata_search_entities",
      "mcp__wikidata__wikidata_get_entity",
      "mcp__wikidata__wikidata_get_labels",
      "mcp__wikidata__wikidata_get_statements",
      "mcp__wikidata__wikidata_get_sitelinks",
      "mcp__wikidata__wikidata_resolve_external_id"
    ],
    "ask": [
      "mcp__wikidata__wikidata_sparql_query"
    ],
    "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 wikidata. Review it before you use it.

Capability tags behind 7 rules
  • mcp__wikidata__wikidata_search_entities untrusted-input
  • mcp__wikidata__wikidata_get_entity untrusted-input
  • mcp__wikidata__wikidata_get_labels untrusted-input
  • mcp__wikidata__wikidata_get_statements untrusted-input
  • mcp__wikidata__wikidata_get_sitelinks untrusted-input
  • mcp__wikidata__wikidata_sparql_query untrusted-input
  • mcp__wikidata__wikidata_resolve_external_id 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/wikidata-mcp-server/verify?hash=6814c605b0f8402de380ac8f42c7406ad82157f062ffb97ea1fbcca21930bef2" | jq -e '.changed == false'

Pinned hash 6814c605b0f8, from Nov 22, 2026, 02:18 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/wikidata-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/wikidata-mcp-server
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.cyanheads/wikidata-mcp-server.svg)](https://radar.anlyon.com/servers/io.github.cyanheads/wikidata-mcp-server)

Source: MCP Registry · repository. Synced Nov 22, 2026, 02:17 UTC.

wikidata-mcp-server: questions and answers

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

Is the wikidata-mcp-server safe?

No scan can promise that. What its definitions show: 7 tools, 1 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the wikidata-mcp-server delete data?

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

Can the wikidata-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 wikidata-mcp-server have?

7 tools: 1 write, 6 read. wikidata_sparql_query, wikidata_search_entities, wikidata_get_entity, wikidata_get_labels, wikidata_get_statements, wikidata_get_sitelinks and wikidata_resolve_external_id.

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

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

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

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

Has the wikidata-mcp-server changed its tools?

Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 22, 2026. Every change is on this page and in its Atom feed.