Wikidata MCP Server
Wikidata MCP サーバー
モデルコンテキストプロトコル(MCP)を用いたWikidata APIのサーバー実装。このプロジェクトは、識別子(エンティティとプロパティ)の検索、メタデータ(ラベルと説明)の抽出、 SPARQLクエリの実行など、Wikidataを操作するためのツールを提供します。
インストール
Smithery経由でインストール
Smithery経由で Claude Desktop 用の Wikidata MCP サーバーを自動的にインストールするには:
npx -y @smithery/cli install @zzaebok/mcp-wikidata --client claude手動でインストールする
まだインストールされていない場合はuvをインストールしてください。
$ curl -LsSf https://astral.sh/uv/install.sh | sh次に、依存関係をインストールします。
$ git clone https://github.com/zzaebok/mcp-wikidata.git
$ cd mcp-wikidata
$ uv sync
# if you want to run client example together
$ uv sync --extra example走る
次のコマンドでサーバーを実行します。
$ uv run src/server.py単純なクライアント コード ( langchain-mcp-adaptersを使用) でテストする場合は、次のコマンドでクライアントを実行します。
# in another shell
$ uv run src/client.pyLLM は有効なエンティティおよびプロパティ識別子を抽出し、Sparql クエリを実行し、最終的にポン・ジュノ監督の映画を推奨します。
{
"messages": [
HumanMessage(
content="Can you recommend me a movie directed by Bong Joonho?",
),
AIMessage(
tool_calls=[
{
"name": "search_entity",
"args": {"query": "Bong Joon-ho"},
}
],
),
ToolMessage(
content="Q495980",
name="search_entity",
),
AIMessage(
tool_calls=[
{
"name": "get_properties",
"args": {"entity_id": "Q495980"},
}
],
),
ToolMessage(
content='["P345", "P244", "P214", "P227", ...]',
name="get_properties",
),
AIMessage(
tool_calls=[
{
"name": "search_property",
"args": {"query": "director"},
}
],
),
ToolMessage(
content="P57",
name="search_property",
),
AIMessage(
tool_calls=[
{
"name": "execute_sparql",
"args": {
"sparql_query": 'SELECT ?film ?filmLabel WHERE {\n ?film wdt:P57 wd:Q495980.\n SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }\n} LIMIT 1'
},
}
],
),
ToolMessage(
content='[{"film": {"type": "uri", "value": "http://www.wikidata.org/entity/Q483761"}, "filmLabel": {"xml:lang": "en", "type": "literal", "value": "Mother"}}]',
name="execute_sparql",
),
AIMessage(
content='I recommend the movie "Mother," which was directed by Bong Joon-ho.',
),
]
}Wikidata MCPツール
サーバーには次のツールが実装されています。
道具 | 説明 |
| クエリで Wikidata エンティティ ID を検索します。 |
| クエリで Wikidata プロパティ ID を検索します。 |
| 指定された Wikidata エンティティ ID に関連付けられたプロパティを取得します。 |
| Wikidata で SPARQL クエリを実行します。 |
| 指定された Wikidata エンティティ ID の英語のラベルと説明を取得します。 |
ライセンス
MITライセンス
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityBmaintenanceA Model Context Protocol server that retrieves information from Wikipedia to provide context to LLMs, allowing users to search articles, get summaries, full content, sections, and links from Wikipedia.22285MIT
- AlicenseNot gradedqualityDmaintenanceA server that implements the Model Context Protocol, providing a standardized way to connect AI models to different data sources and tools.1511MIT
- AlicenseBqualityDmaintenanceProvides access to Wikidata for Large Language Models through the Model Context Protocol, offering tools for entity search, detailed retrieval, SPARQL queries, relation exploration, and property-based searches.54MIT
- FlicenseNot gradedqualityDmaintenanceA production-ready server that provides Wikipedia search and content retrieval tools through the Model Context Protocol, enabling AI assistants to search for articles, list sections, and retrieve specific content.
Related MCP Connectors
Search and fetch Wikidata entities, execute SPARQL queries, and resolve external identifiers.
A Model Context Protocol server for Wix AI tools
Wikidata MCP — wraps Wikidata API (wikidata.org/w/api.php)
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/zzaebok/mcp-wikidata'
If you have feedback or need assistance with the MCP directory API, please join our Discord server