mcp-wikidata
by zzaebok
A server implementation for Wikidata API using the Model Context Protocol (MCP).
What is mcp-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
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
Leave a Comment
Comments section will be available soon. Stay tuned!
Frequently Asked Questions
What is MCP?
MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.
What are MCP Servers?
MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.
How do MCP Servers work?
MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.
Are MCP Servers secure?
Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.
Related MCP Servers
Ableton Live MCP Server
MCP Server implementation for Ableton Live OSC control
Airbnb MCP Server
AI Agent Marketplace Index Search MCP Server
MCP Server for AI Agent Marketplace Index from DeepNLP
Algorand MCP Implementation
Algorand Model Context Protocol (Server & Client)
mcp-server-apache-airflow
pypi.org/project/mcp-server-apache-airflow/
airtable-mcp-server
๐๏ธ๐ค Airtable Model Context Protocol Server, for allowing AI systems to interact with your Airtable bases
Airtable MCP Server
Search, create and update Airtable bases, tables, fields, and records using Claude Desktop and MCP (Model Context Protocol) clients
Alphavantage MCP Server
A MCP server for the stock market data API, Alphavantage API.
Amadeus MCP Server
Amadeus MCP(Model Context Protocol) Server
Anki MCP Server
An MCP server for Anki
Submit Your MCP Server
Share your MCP server with the community
Submit Now