Mcp Wikidata

Mcp Wikidata

What is Mcp Wikidata about?

Mcp Wikidata offers an MCP‑compatible server that wraps common Wikidata operations. It enables clients to programmatically search for entities and properties, list an entity's properties, fetch English labels/descriptions, and run arbitrary SPARQL queries against the Wikidata endpoint.

How to use Mcp Wikidata?

1. Install – either through Smithery:

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

   or manually with uv:

   curl -LsSf https://astral.sh/uv/install.sh | sh
   git clone https://github.com/zzaebok/mcp-wikidata.git
   cd mcp-wikidata
   uv sync
   # optional example extras
   uv sync --extra example
   

2. Run the server:

   uv run src/server.py
   

3. Interact – use any MCP‑compatible client (e.g., LangChain MCP adapters). A sample client script is provided in src/client.py.

Key features of Mcp Wikidata

• search_entity(query) – returns the best‑matching Wikidata entity ID.
• search_property(query) – returns the best‑matching property ID.
• get_properties(entity_id) – lists all property IDs attached to an entity.
• get_metadata(entity_id, language="en") – fetches label and description.
• execute_sparql(sparql_query) – runs a SPARQL query and returns results.
• Fully typed MCP tool definitions for seamless LLM integration.

Use cases of Mcp Wikidata

• LLM agents that need reliable entity resolution (e.g., finding people, places, or concepts).
• Data enrichment pipelines that pull labels/descriptions for IDs.
• Dynamic knowledge queries where an LLM builds a SPARQL query on‑the‑fly.
• Educational chatbots that can retrieve factual information from Wikidata.

FAQ

Q: Do I need an API key? A: No. The server queries the public Wikidata SPARQL endpoint.

Q: Which languages are supported for metadata? A: The get_metadata tool defaults to English but accepts any Wikidata language code.

Q: Can I run multiple instances? A: Yes. The server is a standard Python script; you can start as many processes as needed, each on a different port.

Q: How do I integrate with LangChain? A: Install langchain-mcp-adapters (included in the example extra) and follow the client example in src/client.py.

Q: What Python version is required? A: The project uses uv for dependency management; Python 3.9+ is recommended.

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