Wikidata MCP

What is mcp-wikidata?

mcp-wikidata is a server implementation that allows interaction with the Wikidata API through the Model Context Protocol (MCP). It provides a set of tools to programmatically access and retrieve information from Wikidata, making it easier to integrate Wikidata's vast knowledge base into applications.

How to use mcp-wikidata?

Installation

Via Smithery:

npx -y @smithery/cli install @zzaebok/mcp-wikidata --client claude

Manually:

1. Install uv:

$ curl -LsSf https://astral.sh/uv/install.sh | sh

2. Clone the repository and install dependencies:

$ 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

Running the Server

$ uv run src/server.py

Running the Client (Example)

# in another shell
$ uv run src/client.py

Key Features of mcp-wikidata

mcp-wikidata provides the following tools for interacting with Wikidata:

• search_entity(query: str): Search for a Wikidata entity ID using a query string.
• search_property(query: str): Search for a Wikidata property ID using a query string.
• get_properties(entity_id: str): Retrieve all properties associated with a given Wikidata entity ID.
• execute_sparql(sparql_query: str): Execute a SPARQL query directly on Wikidata.
• get_metadata(entity_id: str, language: str = "en"): Get the English label and description for a specified Wikidata entity ID.

Use Cases of mcp-wikidata

• Knowledge Graph Integration: Easily integrate Wikidata's knowledge into AI applications, chatbots, or data analysis tools.
• Data Extraction and Analysis: Programmatically extract specific data points or entire datasets from Wikidata for research or analytical purposes.
• Intelligent Assistants: Power intelligent assistants or recommendation systems that can leverage Wikidata to answer factual questions or provide relevant suggestions (e.g., recommending movies based on a director).
• Semantic Search: Enhance search capabilities by allowing applications to understand and query information based on Wikidata's structured data.

FAQ about mcp-wikidata

Q: What is the Model Context Protocol (MCP)? A: The Model Context Protocol (MCP) is a framework that allows models (like large language models) to interact with external tools and services. mcp-wikidata implements this protocol to enable seamless communication between AI models and the Wikidata API.

Q: Can I use mcp-wikidata with other AI frameworks? A: While the example shows integration with langchain-mcp-adapters, the underlying MCP design aims for broader compatibility, allowing integration with various AI frameworks that support external tool calls.

Q: What kind of queries can I perform with mcp-wikidata? A: You can perform entity and property searches, retrieve associated properties, and execute complex SPARQL queries, giving you extensive control over the data you retrieve from Wikidata.

Q: Is there a client example available? A: Yes, a simple client example is provided (src/client.py) that demonstrates how to use the tools to answer questions, such as recommending a movie directed by a specific person, by interacting with an LLM and Wikidata.

Wikidata MCP Server

A server implementation for Wikidata API using the Model Context Protocol (MCP). This project provides tools to interact with Wikidata, such as searching identifiers (entity and property), extracting metadata (label and description) and executing sparql query.

---

Installation

Installing via Smithery

To install Wikidata MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @zzaebok/mcp-wikidata --client claude

Installing Manually

Install uv if it is not installed yet.

$ curl -LsSf https://astral.sh/uv/install.sh | sh

Then, install dependencies.

$ 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

---

Run

Run the server with:

$ uv run src/server.py

If you want to test it with a simple client code (with langchain-mcp-adapters), run the client with:

# in another shell
$ uv run src/client.py

The LLM extracts valid entity and property identifiers, executes a sparql query, and finally recommend a movie directed by Bong Joon-ho.

{
  "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 Tools

The following tools are implemented in the server:

Tool	Description
search_entity(query: str)	Search for a Wikidata entity ID by its query.
search_property(query: str)	Search for a Wikidata property ID by its query.
get_properties(entity_id: str)	Get the properties associated with a given Wikidata entity ID.
execute_sparql(sparql_query: str)	Execute a SPARQL query on Wikidata.
get_metadata(entity_id: str, language: str = "en")	Retrieve the English label and description for a given Wikidata entity ID.

---

License

MIT License