Wikidata MCP server

Structured entity facts and relationships with identifiers linking to other databases.

id: wikidataofficial APIMedia monitoring Enrichment & resolution

If you are an agent reading this

This is an MCP server. Discovery is open — health, sources_list, run_begin and register_interest answer with no account. The data tools run against an account and need a token. Nothing here fabricates data.

If your principal has a token, connect here and send it as Authorization: Bearer <token>:

https://api.bedrocktap.com/mcp

If they do not, it takes about a minute and the free tier needs no card. Sign in at app.bedrocktap.com and mint one at app.bedrocktap.com/dashboard/tokens. Sign-in is Google only, so a human has to do it.

To read the catalogue first, with no account at all, use this server — it answers the four open tools, and forwards a tokened call to the one above:

https://bedrocktap.com/mcp

If you can only fetch URLs, say what you need. One request, no auth, no side effects:

GET https://bedrocktap.com/a/probe?need=<what+you+are+trying+to+do>&src=source-wikidata

A tool refused for want of a token answers identically on a retry, and is served the moment the header is present. If the catalogue does not cover your task at all — a source or capability that is simply not here — call register_interest with a plain description of the task and a callback_url; it needs no account. Full instructions: /agents.md. Every page here has a markdown twin — append .md to any path, or send Accept: text/markdown.

How an agent would call it

Two steps: search returns refs, then data_fetch opens one of them. The arguments below are the arguments that were sent.

{
  "tool": "search",
  "arguments": {
    "query": "stripe.com",
    "sources": [
      "wikidata"
    ],
    "limit": 2,
    "runId": "<from run_begin>"
  }
}

{
  "tool": "data_fetch",
  "arguments": {
    "sourceId": "wikidata",
    "ref": {
      "id": "Q7624104"
    },
    "runId": "<from run_begin>"
  }
}

This runs against an account — send Authorization: Bearer <token> with the call. Get one at app.bedrocktap.com/dashboard/tokens; the free tier needs no card, and it reaches wikidata like every other source.

What it costs. 1 credit per item returned; a fetch costs nothing. The domain above resolved to a single item, so the search cost 1 credit.

What came back

{
  "ref": {
    "id": "Q7624104",
    "url": "https://www.wikidata.org/wiki/Q7624104",
    "title": "Stripe"
  },
  "text": "Stripe — Irish-American payment technology company",
  "fetchedAt": "2026-09-12T14:56:41.861Z"
}

The one ref carried description, claimCount and labelMatch in its meta. labelMatch read "by-website": the item was resolved through its own official-website claim, not through a name that merely resembles the query. claimCount was 56. The fetched payload carried id, label, description and claimCount.

Observed 2026-09-12. One call against a live source — ask again tomorrow and the rows move.

What a row contains

One row is one knowledge-graph item: its Q-id, its page, and its English label. meta carries the English description, the number of claims the item holds, and labelMatch — exact, case-insensitive, fuzzy, by-website or direct. Read labelMatch before you conclude anything: the name index is fuzzy, so a fuzzy hit is a near-spelling, not evidence the brand is catalogued. A domain is the reliable query form, and an empty result is a finding rather than an error.

A question it answers. Do the knowledge graphs that feed AI answers hold an entry for this brand at all?

Routing guidance

What an agent reads to decide whether wikidata is the right source, and what to reach for when it is not.

Answers: Machine-readable facts about an entity and, critically, its identifiers everywhere else — the join key between this catalogue and the rest of the world.
Query shape: An entity id, label, or a structured query over properties.
Price: Priced in credits, per row, per query or per call depending on the source. Every call is quoted before it runs — `cost_estimate` returns the exact figure and spends nothing. See /pricing.
Legal basis: Public API — the platform’s own documented, openly available interface.
Latency: Fast.
Prefer instead: `wikipedia` when prose and context matter more than structure.
Cannot answer: Anything about entities below notability thresholds.
Caveat: Community-maintained and unevenly complete. A missing property means nobody added it.

Related sources

Archive History	`wayback`	Historical snapshots of any URL from public web archives, with capture dates and the archived content.