Wikidata MCP Server
위키데이터 MCP 서버
모델 컨텍스트 프로토콜(MCP)을 사용하는 Wikidata API 서버 구현입니다. 이 프로젝트는 식별자(엔터티 및 속성) 검색 , 메타데이터(레이블 및 설명) 추출 , SparQL 쿼리 실행 등 Wikidata와 상호작용하는 도구를 제공합니다.
설치
Smithery를 통해 설치
Smithery를 통해 Claude Desktop에 Wikidata MCP 서버를 자동으로 설치하는 방법:
지엑스피1
수동 설치
아직 설치되지 않았다면 uv 설치하세요.
$ curl -LsSf https://astral.sh/uv/install.sh | sh그런 다음 종속성을 설치합니다.
$ 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 example달리다
다음을 사용하여 서버를 실행합니다.
$ uv run src/server.py간단한 클라이언트 코드( langchain-mcp-adapters 사용)로 테스트하려면 다음을 사용하여 클라이언트를 실행합니다.
# in another shell
$ uv run src/client.pyLLM은 유효한 엔터티 및 속성 식별자를 추출하고, sparql 쿼리를 실행한 후, 마지막으로 봉준호 감독의 영화를 추천합니다.
{
"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.',
),
]
}위키데이터 MCP 도구
서버에는 다음 도구가 구현되어 있습니다.
도구 | 설명 |
| 쿼리로 Wikidata 엔터티 ID를 검색합니다. |
| 쿼리로 Wikidata 속성 ID를 검색합니다. |
| 주어진 Wikidata 엔터티 ID와 연관된 속성을 가져옵니다. |
| Wikidata에 SPARQL 쿼리를 실행합니다. |
| 주어진 Wikidata 엔터티 ID에 대한 영어 라벨과 설명을 검색합니다. |
특허
MIT 라이센스
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